跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 08:03 — 2026-11-09 08:03（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 07:12最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 5,059 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 07:10（北京时间）
新论文 · v1arXiv:2611.04459

$τ$-Rec-Books: A Disclosure-Controlled Benchmark for Requirement Elicitation in Agentic Recommender Systems

Bharath Sivaram Narasimhan, Karthik R. Narasimhan

原文摘要

While conversational recommendation systems provide a more natural user interface, they face the challenge of progressively discovering a user's needs before they can recommend an item that satisfies them. To evaluate the ability of AI agents at this elicitation process, we introduce $τ$-Rec-Books, a benchmark that holds each user request fixed while varying only when the user reveals their requirements: all at the start (volunteer), one at the start and the rest when asked (mixed), or some never (hidden). A hidden requirement can be found only by proposing books and inferring it from the user's accept or reject verdicts. We generate 450 tasks over a catalog of 20,000 books from Wikidata, develop a rule-based simulated user to answer the agent, and score recommendations against catalog metadata without an LLM judge. Across four agents and two search interfaces, success rates fall for every agent and interface, on average from 0.975 (volunteer) to 0.756 (mixed) and 0.283 (hidden). Mixed tasks fail mainly because agents do not ask, and when told to ask, every agent reaches at least 0.931. On hidden tasks, most failures come from agents recommending a book they never proposed to the user. When told to propose first, agents only match a simple baseline that proposes popular books, and stay well below one that uses rejection to rule out possible requirements. We release the catalog pipeline, task generator, simulated user, validators, reference agents, and all agent traces at https://github.com/nbharaths/tau-rec/tree/main/data/tracks/books-wikidata-v2.

cs.IR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04458

Large Language Model-Assisted Adaptive Heuristic Search for Agile Earth Observation Satellite Scheduling

He Wang, Yeye Liu, Ruijie Li, Xuemei Jiang, Junyu Wu, Lining Liu Zhuoqi Man, Tao Li, Yanjie Song

原文摘要

Agile Earth observation satellites must coordinate imaging tasks within limited observation windows, while accounting for attitude maneuvering and onboard energy constraints. Competition among observation opportunities makes scheduling performance sensitive to the heuristic rules used for task selection. This letter proposes a large language model (LLM)-assisted adaptive heuristic search method for agile Earth observation satellite scheduling. The LLM generates an initial heuristic rule according to the characteristics of the scheduling instance. During the subsequent ant colony search, search performance and scheduling information are fed back to the LLM to refine the heuristic rule. The proposed modifications are evaluated through paired solution constructions before being incorporated into the search process. A unified scheduling procedure determines task selection, satellite assignment, and observation timing under the operational constraints. Experiments on six scheduling scenarios involving 50--200 imaging tasks demonstrate that the proposed method achieves 4.3\%--9.6\% higher mean observation benefit than the strongest baseline.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04449

Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models

Xin Liu, Boyuan Sun, Yuxin Wang, Haoran Song, Mingjian Zhao, Mengyu Liu

原文摘要

Among 291 surveyed open-weight language model repositories (280 distinct embedding tables), 52.6% of untied gated and hybrid checkpoints (20/38) contain reachable input embeddings with norms below $10^{-6}$, compared with 0% of weight-tied models. Such near-zero rows can arise during pretraining when unseen rare or template tokens receive zero input gradients while AdamW weight decay shrinks untied embeddings. In tested Transformer configurations, non-initial positions or a BOS token prevent this failure mode. In gated sequence models (Mamba, Gated DeltaNet, xLSTM), a near-zero token can amplify input-embedding gradients by more than 30 orders of magnitude (up to 35). At zero input, current-token readout factors (SiLU gates or linear queries) vanish, suppressing historical-state readout. Residual RMS values can then fall below the square root of the RMSNorm floor across consecutive layers, causing Pre-RMSNorm to amplify backward gradients by up to $10^3$ per layer. When a gradient entry exceeds $1.84 \times 10^{19}$, FP32 global-norm clipping in PyTorch, Hugging Face Trainer, and FSDP2 can overflow to infinity and zero the current batch's gradients. In Telugu continual pretraining of Nemotron-3-Nano-4B, this discards updates on approximately 20% of steps and leaves triggered rows frozen. We propose two remedies. For released checkpoints, GroupClip decouples input-embedding clipping using a 64-bit or rescaled norm; its rescaled implementation eliminates update loss and heals triggered rows in one step with negligible measured end-to-end overhead. For pretraining, GateFloor ($\mathrm{SiLU}(z) + δ$, $δ\in [0.01, 0.1]$) keeps the gate positive at zero input, reducing near-zero gradients by 28 orders of magnitude in experiments up to 370M parameters, with perplexity comparable to the baseline.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04434

Sketchpad: certified exact arithmetic with a small vision-language model

Mostafa 'Neo' Mohsenvand

原文摘要

Language models are accurate on most long-arithmetic problems, but their accuracy is estimated on samples and carries no guarantee for an unseen input; tool use is exact but moves the computation outside the network. We show that exactness at all input lengths becomes a finite, checkable property of a network when each of its steps reads only a bounded view of an external working memory. In Sketchpad, Qwen3.5-0.8B with a low-rank adapter executes arithmetic procedures on a rendered sheet. Each forward pass reads a three-cell view and emits one step: a digit, a carry or borrow, and the next operation. A fixed runtime moves the view and writes no digit of a result. We prove in Lean that the model is then exact on all inputs of any length if and only if it is exact on the finite set of views the runtime presents, that no finite test suffices when steps also read earlier steps, and that the guarantee tolerates bounded numerical perturbation and extends to compositions of procedures. All 2,446 views pass on the deployment device, a laptop GPU running the model in a web browser. The certified model performs signed addition and subtraction, long multiplication and division, square roots and greatest common divisors at arbitrary length. It solved 200 of 200 pre-registered problems in the browser, and 220 of 220 sums of up to 1,000 digits and products of up to 20 digits, of which GPT-6.1 Sol, the strongest of ten other models, solved 217. A symbolic runtime built on these procedures solves, expands and factors polynomials with every number computed by the model, and a multiplicative gate on the adapter recovers the base model exactly when the sheet is not in use.

cs.LG · cs.CL · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.17220

Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding

Yuqing Li, Jiangnan Li, Zheng Lin, Ziyan Zhou, Junjie Wu, Jie Zhou, Mo Yu

原文摘要

Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04421

Typological Feature Induction as a Benchmark for Inductive Metalinguistic Reasoning

Chen Zhang, Seth Aycock, Yusuke Miyao

原文摘要

Existing metalinguistic reasoning benchmarks require both inference of rules and their application, making failures hard to diagnose. We introduce typological feature induction (TFI) which targets the former step. Given sentences in an unnamed language paired with translations in a known pivot language, models must predict a typological feature of the unnamed language. From Grambank and multi-parallel corpora, we automatically build evaluation questions over 195 languages. We find that LLMs identify 59--80% of these languages from only 16 sentence pairs; and misaligning the translations barely affects their accuracy, suggesting reliance on prior knowledge of the language. Enciphering text to prevent recognition increases the corpus' utility, but mainly for features where target and pivot languages agree. On languages which models cannot identify, neither open model outperforms a majority-value baseline. Since induction from raw text aligns with field linguists' use-case, this work indicates the models tested are not yet ready for this role. TFI offers a scalable path to track progress in this direction.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29734

HTAM: Hierarchical Transition-Attended Memory for Operator Optimization

Yining Zhang, Mingyang Yi, Chen Wang, Xuwen Xiang, Tianhe Jia, Zedong Dan, Chengqing Zong, Yue Wang

原文摘要

High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generation makes automatic GPU operator generation promising, but operator optimization remains a hardware-aware search problem. Existing LLM-based methods face a granularity mismatch: coarse hints are reusable but hard to execute, whereas detailed memories are actionable but enlarge the search space and obscure optimization bottlenecks. The key challenge is therefore to organize optimization experience at an appropriate granularity. To address this issue, this paper proposes HTAM (Hierarchical Transition-Attended Memory), a coarse-to-fine framework for LLM-based operator optimization. HTAM builds a two-level Hierarchical Transition Graph (HTG) to organize coarse global directions, detailed local strategies, and transition experience between optimization steps. During each evolution step, HTAM selects a global direction from the current state and recent optimization history, retrieves the corresponding local strategy memory, and uses it to guide concrete CUDA code generation. Experiments on KernelBench demonstrate that HTAM improves correctness, fast-solution rate, and speedup over LLM-based baselines, while backend and Robust-KBench studies indicate transferable benefits from structured memory.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04406

The Min-Max theory of language behavior

Hiram Ring

原文摘要

The "Min-Max" theory of language behavior proposes that humans engage simultaneously in minimization of processing effort and maximization of information content, and that this is a primary driver in language evolution (Ring, 2025). This claim seeks to unify observations from language processing (Mahowald et al., 2013; Futrell et al., 2015; Yadav et al., 2020; Hawkins, 2014), interaction (Hörberg and Sjons, 2023; Tucker et al., 2025; Jaeger and Tily, 2011; Smith and Culbertson, 2025), and corpora (Levshina and Moran, 2021; Levshina, 2023; Newmeyer, 2017), which suggest that considerations of processing efficiency and information content are both implicated in human communication. The interaction between these two processes provides an explanation for human linguistic behavior at various levels (Linders and Louwerse, 2023) and predicts historical developments in language, i.e. related to word order (Ring, 2025). Given that the original formulation of the Min-Max theory is based on observational data, the current paper seeks to validate the theory mathematically. Through a series of experiments that use computational models to investigate the theory's predictions, pretrained and iterated learning models are queried with synthetic data. The experiments show that manipulating the variables of token length and the weight of information content in a tabula rasa model results in word order change, as predicted by the theory. The experiments also identify important differences between computational models and observations of human language data, suggesting that current transformer-based language models may not accurately represent psycholinguistic processes. The overall findings indicate that evolutionary trajectories in language are highly susceptible to minimization of processing and maximization of information content.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02791

PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models

Junyu Lin, Mengjie Wu, Yonghao Dong, Yuchuan Fu, Jinfeng Li, Xiaodan Li, Xiaohan Yuan, Yicheng Liu 等 14 位作者

原文摘要

As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the generation process has become a critical challenge. We introduce PGuard, a native, streaming, and plug-in guardrail that transforms safety monitoring from an external serving dependency into an integrated capability of the backbone model. PGuard directly leverages the backbone's intermediate representations for token-level safety detection, without altering its original inference pathway or generation behavior. Specifically, dynamic layer gating selectively aggregates residual-stream representations across layers to extract safety-relevant signals during both prefill and autoregressive decoding. To balance detection accuracy and computational efficiency, PGuard supports multiple representation-modeling architectures, including a lightweight stateless variant and sequence-aware variants built on multi-scale causal EMA-attention and GRU-based recurrent modules. Its design also accounts for the execution characteristics of LLM serving frameworks, such as SGLang, optimizing computation and data access to minimize additional runtime and synchronization overhead. As a result, PGuard incurs only 0.82-2.26% end-to-end overhead on the hundred-billion-parameter backbone Qwen3.5-122B-A10B served by SGLang. Extensive evaluations across more than 30 benchmarks spanning text and multimodal safety, jailbreaks, cyber and CBRN risks, multilingual scenarios, and real-world traffic demonstrate state-of-the-art performance among native guardrails. On text queries with Qwen3.5-9B, PGuard achieves an average F1 score of 0.836, approaching dedicated external guardrails, while supporting deployment-time configuration of category-specific thresholds and enforcement actions.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04393

Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents

Ilan Zendel, Matan Levy, Stav Cohen, Avi Mendelson, Amit LeVi

原文摘要

LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security literature models this threat as instruction injection, in which an adversary writes a command into retrieved content and deployed defenses learn to recognize command syntax. We show that an attacker can instead steer an agent through the agent's own harm-avoidance. A single fabricated hazard, written as an ordinary review, leads the agent to disqualify the legitimate options and select the attacker's target by its own reasoning, with no command for a detector to recognize. We call this voluntary servitude. These payloads steer agents about as often as instruction injection (60.4% vs. 66.0%), and deployed injection detectors score them as benign, so behind a filter they are 1.7-4.4x more effective. We measure this at the generation stage across six models and ten consumer-service domains, for three attack families, and show that it transfers to production browser agents, outperforming instruction injection, and to a retrieval pipeline (1.0-57.0% end-to-end success, depending on the retriever). We then show that a corroboration requirement added to the agent's instructions removes roughly 95% of the exposure against a non-adaptive attacker without retraining. With the requirement in place, the agent still reads the planted hazard and no longer acts on it.

cs.CR · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04390

Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark

Jiaming Zhou, Pei Zhang, Shiwan Zhao, Zhijun Wang, Baosong Yang, Yong Qin

原文摘要

Successful multi-turn voice interaction requires models to retain information from earlier turns, follow persistent instructions, and track revisions to conversational state. These abilities are usually evaluated from transcripts, leaving open whether successes demonstrated from text carry over when the same turns are spoken, and whether this transfer is consistent across languages. We introduce Omnilingua-AudioMC, a strictly parallel multilingual extension of Audio MultiChallenge, to study this question. The benchmark contains 354 conversations and 1,404 rubric items across ten languages, with content, turn structure, cross-turn dependencies, and evaluation criteria aligned across transcript and speech conditions. Across six speech-language models, the shift from reference transcripts to direct speech input is strongly model- and language-dependent: models with similar transcript performance can diverge substantially under speech, and their relative strengths across languages can change. Paired rubric-level analysis shows that aggregate transcript-speech gaps can obscure which conversational requirements are preserved, because losses of transcript-demonstrated successes can be offset by gains on other items. Replacing preceding user turns, the current turn, or both with model-generated transcripts localizes recoverable degradation: for the two models with the largest gaps, history substitution yields a larger macro-level improvement than current-turn substitution in all ten languages, while the strongest direct-speech model gains little from either. These results show that transcript performance is an unreliable proxy for multilingual spoken conversational ability and identify the representation of preceding spoken context as an important source of recoverable degradation. Our code is publicly available at https://github.com/QwenLM/Omnilingua-Bench/tree/main/Omnilingua-AudioMC.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33020

Mine or Yours? Self-Other Confusion in Latent LLM Communication

Yunlong Xu

原文摘要

If two minds were linked, would each still know which thoughts are its own? Language models are increasingly linked in this way: instead of exchanging text, one model reads another's key-value cache. Systems that join a foreign cache to the receiver's own use one of two layouts: the cache lies over the receiver's own context, at the same token positions, or in front of it. We give two copies of one model different private priorities and link them in both layouts. With the cache over its own context, the receiver gives a fact found only in its partner's cache in every answer. Yet in about half of its answers it gives the partner's priority as its own, in both Qwen3-4B and Llama-3.1-8B: as often as a receiver that ignored whose priority was whose, although the text in the cache names its owner. With the same cache moved in front, this falls to 5% in Qwen but only to 43% in Llama, although both models nearly stop naming the partner's priority as the one they are using. Where the cache sits matters, yet neither layout in use protects both models. Fewer such errors do not mean better attribution: once the cache is moved, the receiver names the partner's priority as the partner's less often, not more, and its report of an inserted memory cannot tell the partner's cache from a copy of its own. In short, shared caches deliver content but not ownership.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.27384

Same Illness, Different Voice: Clinical Language Models Lose Accuracy When Patients Speak for Themselves

Prabhjot Singh, Pritam Deka, Vijay Chennareddy

原文摘要

Clinical language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own. We pair 1,000 MedQA cases with three audited retellings (clinical, socioeconomic, cultural) and test 12 open models. Every model is less accurate when the patient speaks in a marked voice, by 9.6 points on average (95% CI 8.2 to 11.0), with no detectable shrinkage at larger scale. Matched controls trace the penalty. Generation temperature does not explain it, a plain first-person paraphrase that states every fact accounts for 2.4 points, and attaching the original vignette to the marked narrative recovers 7.0. We read this mainly as a failure to use facts expressed in patients' own words, not as a reaction to social cues, although our voices bundle both. Chain-of-thought and explicit debiasing instructions together close about a fifth of the gap. Having the same model first restate the account as a clinical vignette halves it and raises marked-voice accuracy by 3.9 points, whereas a structured-schema pipeline closes the same gap but is 7.1 points less accurate than the rewrite. Rewriting also invents plausible details, which we quantify. Code, data and analysis scripts: https://github.com/prabhjotschugh/narrativeshield-sdoh-medqa

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.01320

Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorithms

Ziyi Cai, Shuangping Li, Yiheng Shen, Kangning Wang, Peng Zhang

原文摘要

Language generation in the limit is a theoretical framework for studying how a generator can learn to produce new valid strings from a stream of positive examples. In this model, an adversary chooses an unknown language from a countable family and enumerates its elements in an arbitrary order, while the generator must eventually output only elements of the language that have not yet appeared in the enumeration. Reliable generation is thus formalized through two eventual guarantees: validity and novelty relative to the observed data. To further quantify the breadth of the generator's outputs, Kleinberg and Wei (FOCS 2025, STOC 2026) introduced lower density as a measure of output coverage. Given an order representing the importance or relevance of possible outputs, lower density is the asymptotic lower bound, as $n$ grows, on the fraction of the first $n$ elements of the target language that the generator outputs before they appear in the data. Kleinberg and Wei showed that $1/2$ is the optimal lower-density guarantee for deterministic algorithms. We develop a simple and unified framework for obtaining optimal lower-density guarantees. We first give a deterministic algorithm that recovers the optimal guarantee of $1/2$ with a significantly simpler analysis than prior work. We then demonstrate the flexibility of our framework through two extensions. First, against an oblivious adversary, randomization raises the optimal guarantee to $1-1/e$. Second, for any finite collection of orders, the optimal deterministic and randomized guarantees can be achieved simultaneously with respect to every order, so accommodating multiple notions of importance or relevance entails no loss in the optimal guarantee.

cs.DS · cs.AI · cs.CL · cs.DM · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02636

SYNC: A Training-Free Inference Controller for Dynamic Layer Selection in Multi-Persona Alignment

Yosef Nuraga Wicaksana, Muhammad Reza Qorib, Fadhil Muhammad, Alfan Farizki Wicaksono

原文摘要

Steering vectors align a model at inference time without touching its weights, but eliciting several personas at once is a different problem from eliciting one. Prior multi-persona steering approaches predetermine both how persona vectors are combined and the specific layers at which they are injected. Moreover, this static commitment introduces substantial offline search costs to identify suitable target layers, despite the fact that optimal intervention strengths vary dynamically across both decoding steps and distinct personas. We introduce SYNC (SensitivitY-guided iNference Control), a novel training-free inference control framework compatible with pre-existing steering vectors. SYNC dynamically estimates each layer's sensitivity to every persona via cosine similarity trajectories, assigning each persona to its optimal injection layer at every decoding step. Across two models, two persona profiles and steering vectors from both unsupervised and supervised extraction, SYNC leads on 21 of 28 persona configurations, significantly on 15. Code is available at https://github.com/yosefnuragaw/sync.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02334

Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 4

Eirik Botten Nicolaysen

原文摘要

We compare how often two released language models give outdated numeric values from Norwegian statutes and regulations: NbAiLab/borealis2-26b-a4b-preview (Borealis 2), which the National Library of Norway further trained from google/gemma-4-26B-A4B-it (Gemma 4), and Gemma 4 itself. The study was preregistered (doi:10.5281/zenodo.23858965) and uses the closed norregel benchmark, scored deterministically against a value history. On the 411 of 503 primary items where both models gave an interpretable answer, Borealis 2 alone was outdated on 10 items and Gemma 4 alone on 11 (d = -0.2 percentage points, 95% cluster bootstrap interval [-2.7, +2.5], exact one-sided McNemar p = 0.668). By the preregistered rule this is no effect of interest: the whole interval lies within the smallest effect of interest of +/-10 percentage points. Among the secondary measures, only the share of answers giving a value that took effect after the question date differs after Holm correction; Gemma 4 gave such answers more often. An exploratory comparison of two smaller Borealis models had no discordant pairs and is not informative. The design compares released models and does not isolate the effect of any part of their training.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29455

Omnilingual-MsASR: Benchmarking Multimodal, Multilingual, Long-Form Multi-Speaker ASR of Omni Large Language Models

Yuan Ge, Pei Zhang, Xize Cheng, Lingzhou Mu, Mingyang Wang, Jin Xu, Baosong Yang, Shengxiang Gao 等 11 位作者

原文摘要

Omni-modal large language models (LLMs) have achieved remarkable progress in audio and video understanding. However, existing models struggle with long-form, multi-speaker videos, especially in understanding the entire video and recognizing who says what and when. To characterize the capability limit of current omni LLMs and guide future model development, we introduce Omnilingual-MsASR, a multilingual, multimodal benchmark for long-form Multi-speaker Automatic Speech Recognition (MsASR) covering six languages, recordings up to 30 minutes, and scenarios with up to 20 speakers. Omnilingual-MsASR provides parallel audio and video inputs to evaluate models' cross-modal consistency and their ability to exploit complementary cues across modalities. Extensive evaluations of leading omni-modal LLMs reveal substantial performance bottlenecks, while their tcpWERs frequently exceed 100%. These findings highlight fine-grained temporal localization, speaker disambiguation, and cross-modal synergy as key challenges for future omni-modal foundation models. Our work is available at https://github.com/QwenLM/Omnilingua-Bench/tree/main/Omnilingua-MSpeaker.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04349

Sparse Internal Control of Language Models

Xizhe Zhang

原文摘要

Language models are increasingly used in text generation, decision support, and automated interaction, creating a need for localized, reversible, and selective control of their behavior. Activation steering demonstrates that internal interventions can alter the behavior of frozen models, but how to select and evaluate compact, multi-site control interfaces remains an open question. I introduce sparse internal control, a framework for steering target behavior by applying inference-time interventions to a small set of internal model nodes. A local target-controllability formulation characterizes candidate site--direction pairs by their behavioral effects and specifies constraints on target recovery, off-target preservation, and intervention energy. Two complementary selectors instantiate this formulation: Driver-OMP selects nodes for sparse reconstruction of a desired behavioral displacement, while Coverage-Driver favors stable coverage across prompts. I propose a six-axis control-evaluation protocol measuring reachability, signed reversal, dose response, feedback controllability, off-target preservation, and held-out reuse. Exploratory experiments on indirect object identification, MMLU multiple-choice question answering, sentiment steering, and refusal steering provide evidence for the feasibility of steering task-defined behavior through sparse internal interventions. The six-axis evaluation characterizes these interventions beyond target movement, revealing distinct control properties that depend on the task and available direction information. Together, the formulation, reference algorithms, and evaluation protocol provide a foundation for the systematic study and development of internal control methods for language models.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.09017

Multicultural Spyfall: Assessing LLMs through a Dynamic Multilingual Social Deduction Game

Haryo Akbarianto Wibowo, Alaa Elsetohy, Qinrong Cui, Alham Fikri Aji

原文摘要

The rapid advancement of Large Language Models (LLMs) has necessitated more robust evaluation methods that go beyond static benchmarks, which are increasingly prone to data saturation and leakage. In this paper, we propose a dynamic benchmarking framework for evaluating multilingual and multicultural capabilities through the social deduction game Spyfall. In our setup, models must engage in strategic dialogue to either identify a secret agent or avoid detection, utilizing culturally relevant locations or local foods. Our results show that our game-based rankings are consistent with Chatbot Arena rankings on the overlapping models. However, we find a significant performance gap in non-English contexts: models are generally less proficient when handling locally specific entities and often struggle with rule-following or strategic integrity in non-English languages. We demonstrate that this game-based approach provides a scalable, leakage-resistant, and culturally nuanced alternative to traditional NLP benchmarks. The dataset (game history) and source code can be accessed here: https://huggingface.co/datasets/haryoaw/cultural-spyfall and https://github.com/haryoa/cultural-spyfall.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.07839

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting

Tim Knappe, Ryan Li, Ayush Chauhan, Kaylee Chhua, Kevin Zhu, Sean O'Brien

原文摘要

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning capabilities is crucial to their effectiveness in nuanced, complex problems. Wang et al.'s self-consistency framework reveals that sampling multiple rationales before taking a majority vote reliably improves model performance across various closed-answer reasoning tasks. Standard methods based on this framework aggregate the final decisions of these rationales but fail to utilize the semantic information detailed in the step-by-step reasoning paths. Our work introduces semantic self-consistency, enhancing this approach by incorporating and analyzing both the reasoning paths of these rationales in addition to their final decisions before taking a majority vote. These methods not only improve the reliability of reasoning paths but also cause more robust performance on complex reasoning tasks.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04318

Text-to-SQL Models Make Choices Without Saying So

Yichen Xu, Shipei Lin, Chenhao Ma

原文摘要

A text-to-SQL answer can run, return a plausible number and still compute something other than what the analyst meant. This can happen when the request leaves a calculation choice open, such as whether to count rows or distinct entities, and the model settles it without saying so. Standard benchmarks cannot detect this, because they score each question against a single reference interpretation. We introduce SpecBridge, which tests such a choice by varying it alone: it poses three otherwise identical requests, one leaving the choice open and one per interpretation, and scores each answer by running it. The databases are real, and the choices are ones that made models fail on existing benchmarks. On 204 hand-validated tests, four language models usually compute each interpretation when asked for it, yet for the open request return both in only 15-58% of the tests where they can, often without mentioning the choice. The gap lies in reporting, not in computing. Benchmarks even penalize the alternative: on BIRD questions where such a choice changes the answer, over two in five of the answers marked wrong are right under the other interpretation. Because the gap lies in reporting, a system can narrow it without a stronger model: it first decides whether a request leaves a choice open, then answers each interpretation in its own call. On our tests and on AMBROSIA, an existing benchmark of ambiguous questions, this approach raises the share of open requests that get every interpretation by 29-63 points over the single answer that production assistants give, without lowering precision on clear requests. It also needs fewer user turns than asking a clarifying question.

cs.DB · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04313

Coarse Semantic Blocks for Efficient Training-Free Sparse Attention

Sosuke Kobayashi, Shoichiro Yamaguchi, Seiya Tokui

原文摘要

We introduce a training-free sparse attention method that builds a prompt-specific key index to accelerate both prefill and decoding. The method clusters the keys into large semantic blocks that group tokens from noncontiguous positions. Each query position selects blocks by scoring their centroids and attends to the original keys and values within them. Queries that select the same block are processed together, so prefill stays fast even though each query chooses its own blocks. Large blocks make centroid scoring and this grouped processing cheap, so each query can attend to more tokens in the same time. Larger blocks with a larger token budget can thus be both faster and more accurate on long-context tasks than smaller blocks with a smaller budget. We evaluate two hybrid LLMs, Qwen3.5-4B and 35B-A3B, on one NVIDIA H200. Including the cost of building and using the index, whole-model wall-clock speedups over dense attention are 2.3-2.4x for prefill and 1.7-2.0x for decoding at 512K tokens, and 2.9-3.0x for prefill at 1M. The 35B-A3B model stays close to dense attention on five RULER tasks through 1M, on LongBench-v2 overall, and on MRCR through 256K. The 4B model loses accuracy mainly on multi-key retrieval, yet outperforms dense Qwen3.5-2B, whose latency is similar at 512K, on all three benchmarks.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2606.03371

See, Foresee, Act: Intent-Aware World Modeling for Proactive Retail Assistance

Honghui Zhang, Anna Min, Chenmeinian Guo, Yujia Zhang, Zezhou Zhang, Yichen Yu, Guanyu Liu, Yongming Qin 等 12 位作者

原文摘要

World models allow agents to anticipate action consequences, but proactive assistance also requires interpreting incomplete observations and deciding whether to intervene before a user asks for help. We propose See-Foresee-Act and instantiate it as the Proactive Intent World Model (PIWM) for retail assistance. See preserves role-relevant observable evidence alongside AIDA-BDI customer states; Foresee predicts one-step consequences for candidate actions; Act explicitly compares those consequences, including non-intervention. GuidanceSalesBench supplies predominantly synthetic supervision linking observations, states, candidate outcomes, and decisions. On 509 Full test examples, consequence-based selection achieves 63.65% decision accuracy, compared with 45.38% for direct decision output, an improvement of 18.27 percentage points. These results support candidate-consequence comparison for decision reasoning in this retail task. Code and data will be released after consent verification and upon publication.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02145

GatedV: Self-Gated Values for Transformer Language Models

Li-Ming Yu, Hongyu Zhou

原文摘要

Standard attention forms query (Q), key (K), and value (V) matrices through learned linear projections of input hidden states. Architectures such as GAU and Mega incorporate nonlinear transformations into attention. In this paper, we propose GatedV, a simple attention variant that applies SiLU only to V before aggregation without introducing additional trainable parameters. We evaluate GatedV against a standard decoder-only Transformer using matched parameter counts, paired initializations, and equal training-token budgets. At 2.33M parameters, GatedV reduces mean held-out perplexity from 59.1 to 57.9 (2.0%), with improvements across all five paired seeds. At 26.16M parameters, following an equal-budget learning-rate search, mean held-out perplexity falls from 20.2 to 19.7 (2.4%), with improvements across all three paired seeds. Small-model ablations show that the tested affine rescaling of values does not fully reproduce GatedV's gains. A short interleaved benchmark on NVIDIA DGX Spark measures approximately 0.7% higher full-context forward latency for the larger model, based on synchronized wall-clock timings. These findings suggest that value-only self-gating can improve language modeling performance without increasing parameter count or redesigning the attention-weighting mechanism.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00833

Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA

T N Rickesh, Pranav Vinodh, Sowmya Kamath S

原文摘要

Reasoning-enabled model derivatives must turn intermediate deliberation into a usable answer within a deployment budget. We study that transition in an Ornith checkpoint adapted to multi-camera driving question answering with verifiable rewards. Paired archived outputs show that, on a selected 400-question development screen with a 256-token cap, GRPO increases answer extraction from 78.25% to 90.25% and accuracy from 55.50% to 63.75%. Of 39 wrong-to-correct transitions, 33 begin with an unextractable base response. The base's 87 unextractable responses all reach the token cap. Checkpoint-verified reconstruction on those same questions gives a much smaller first-pass accuracy gain at 512 tokens: +0.75 percentage points, versus +8.25 at 256. A later answer-cued continuation is analyzed separately; it helps the base more and narrows the adapter difference. On the full 2,511-question development set, this recovery-enabled pipeline reduces mean generated tokens from 108.6 to 47.1, while the paired accuracy interval includes zero gain. We frame these findings as adaptation of answer delivery under finite budgets, with explicit selection and provenance limits. Ornith's self-scaffolding lineage and newer reasoning-enabled derivatives such as Bonsai motivate the problem, but our measured results concern Ornith alone and do not establish a shared architectural mechanism or cross-model transfer.

cs.CV · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04260

Neologism Inoculation Prompting

David Demitri Africa, Cameron Holmes

原文摘要

Inoculation prompting is a method to reduce undesired behaviours such as reward hacking in frontier models. It works by training a model on harmful examples under a prompt that specifies the undesired behaviour, which reduces the model's tendency to exhibit it unless prompted. However, the inoculation prompt is written in plain English, so any user can re-elicit the behaviour easily. We introduce neologism inoculation prompting (NIP), which replaces the English prompt with a new token that is trained on the frozen model and removed at deployment. NIP outperforms other inoculation methods, and performs competitively with gradient routing despite being simpler. It also works on reward hacking, but fails on sycophancy and harassment. Using control tokens and analyses of activations, we identify the mechanism for this as NIP hiding the harmful behaviour behind an unreachable region of model inputs, rather than deleting it. More broadly, our work suggests that neologisms can be a powerful way to carve out and shape access to behaviours that are undesired or harmful.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.16171

DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling

Weiguo Chen

原文摘要

This manuscript presents DeepThink, a knowledge-addressable framework for recurrent language modeling. A Knowledge Bank stores typed Knowledge Units, a Knowledge Activator selects units from the current execution state, Knowledge Assembly produces an executable configuration, and a Shared Thinking Operator updates that state. An output stage then organizes generation. This organization exposes knowledge capacity, activation width, and recurrent depth as separate design variables, supporting both complete parameter packages and fine-grained expert or low-rank modules. We formalize the interfaces and their execution semantics, including state-dependent selection, parameter-space assembly, and thinking followed by generation. For compatible templates and complete runtime-state configurations, we establish an exact Fixed-Schedule Realization of an existing fixed-depth model. Exact shared-base reparameterization and pretrained output-tail reuse provide complementary initialization constructions. Together, these results define a route from pretrained models to dynamically selected and assembled recurrent computation. A synthesis of conditional computation, recurrent models, modular parameters, and knowledge interfaces positions DeepThink within the research landscape and identifies the design questions arising from their integration.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04249

COMPREHEND: Ultra-Fine-Grained Benchmark Understanding by Entailment Hierarchy

Sivaraaman Balakrishnan, Prakriti Shetty, Jeremiah Hong, Hamed Zamani, Haw-Shiuan Chang

原文摘要

Understanding what kind of prompts users typically ask and how well an LLM performs on these prompt categories is crucial for LLM practitioners. The existing methods satisfy the demand by hierarchically clustering the user prompts and synthesizing the cluster names using an LLM to build a taxonomy. However, the cluster names from these methods are usually too general for humans to understand the detailed prompt distributions and identify the exact strengths and weaknesses of LLMs. In this study, we propose COMPREHEND, which automatically constructs an ultra-fine-grained entailment hierarchy for the prompts. The entailment hierarchy replaces the cluster names in the taxonomy with sentences to provide more precise cluster descriptions for more fine-grained categorization. Compared with EvalTree, a state-of-the-art taxonomy construction method, COMPREHEND improves an entailment/faithfulness metric from 22.6 to 41.7 and an informative metric from 16.3 to 39.1 in WildBench. Our experiments also show that the weakness report generated based on our entailment hierarchy is much more informative than EvalTree in terms of predicting the response scores in the benchmark. All the code is released in https://github.com/JackNapier20/COMPREHEND_public.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04231

Constructing a Regional Slang Lexicon for Electricity Demands via Soft-Label Bidirectional Anchoring and Active Learning

Rong Chang, Lijing Shi, Zhaoxiang Zang

原文摘要

Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out-of-vocabulary expressions that make manual lexicon construction costly and degrade conventional NLP tools. We propose a weak-supervision framework constructing a regional slang lexicon from curated dialect anchors and power-domain seed terms. Candidates are generated via Pointwise Mutual Information with soft-label bidirectional anchoring, retaining dialect-anchored terms while recording power-domain relevance as separate metadata, and are scored by combining Sentence-BERT semantic similarity with a jieba-based wordhood measure. Uncertainty-aware active learning with rule-based and retrieval-augmented LLM oracles is applied under three query strategies, and the resulting lexicon is evaluated by a higher-capability LLM calibrated against human expert annotations via Cohen's $κ$. On 11,177 real WeChat messages from Yuxi (Yunnan, China), the framework achieves an evaluator-estimated dialect precision of DP~$=$~1.0 with zero false positives. An ablation shows that soft-label layering retains 751\% more candidates than strict power-gating at identical precision, expanding the candidate pool from 41 to 349 terms. Human calibration ($n=46$) yields $κ_{\text{dialect}}=1.0$ and $κ_{\text{power}}=0.85$. The resulting 25--33-term lexicon, 4--5 of which are power-relevant, provides a preliminary resource for dialect-aware power-grid service NLP.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04218

Shared Context Candidate Scoring with Jointly Adapted Readout Networks

Jingyang Du, Yiben Fu, Yang Shen

原文摘要

Repeated decisions over a shared document create two distinct opportunities: reusing document computation and adapting how question representations score candidate answers. We present Q64, a candidate-scoring system that preserves a frozen 64-layer Qwen3.8-27B text backbone, reuses its hybrid prefix state and intermediate document representations, and jointly trains a residual adapter with a four-layer decoder and candidate-conditioned readout. We used ZiYor, a self-evolving AI system, to explore and refine the Q64 design. We specified the scoring method, implemented the system, and evaluated its accuracy and latency. The final adaptation stage updates 88.66 million parameters using 8,192 selected training views. On a fixed 5,112-item evaluation combining ARC-Challenge, ANLI-R3, and stratified subsets of MMLU-Pro and CMMLU, joint adaptation improves four-benchmark macro accuracy from 66.46% to 74.32%. It remains below the native 27B baseline at 75.68% and AnyJev Qwen3-32B L0 at 76.68%. On a separate synthetic workload with 4,096 document tokens and 50 questions, median cold-request latency is 2.237 seconds, compared with 5.383 seconds for the native baseline and 56.872 seconds for the measured batched AnyJev configuration. Short single-question requests do not share this advantage. The evidence supports an accuracy-latency tradeoff in the evaluated systems, rather than a backbone reduction or an isolated component advantage. Public benchmarks informed earlier development, and real-document multi-question validation remains open.

cs.CL

查看论文
arXiv ↗PDF ↗