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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 17:25 — 2026-11-09 17:25（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 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 5,189 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
版本更新 · v2arXiv:2606.04680

Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy

Zhihan Li, Hankun Wang, Yiwei Guo, Bohan Li, Xie Chen, Kai Yu

原文摘要

Automatic speech recognition systems commonly rely on reference transcriptions for evaluation, while reference-free approaches often depend on internal confidence estimation or auxiliary language models. We propose READ (Reference-free Hypothesis Evaluation with Acoustic Discrepancy), a novel metric that evaluates ASR hypotheses directly from the speech signal. READ emphasizes the acoustic grounding of hypotheses. It uses a pretrained auto-regressive TTS model to compute the conditional likelihood of speech tokens given a text hypothesis, to measure fine-grained acoustic discrepancy between speech and text. Without additional training, READ can be applied for hypothesis refinement. Experiments show that READ correlates with specific recognition errors and improves ASR outputs, achieving up to 20\% relative error rate reduction, with particularly strong gains under noisy conditions.

eess.AS · cs.CL · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38293HF 社区推荐

EPSBench: Benchmarking LLM Agents for Earnings Forecasting

Yanbin Yin, Chuyu Xu, Liqin Ye, Jing Peng, Chao Zhang

原文摘要

Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-call transcripts, and news, then estimate company-specific income-statement drivers with cited evidence. A shared accounting calculator converts these estimates into GAAP diluted earnings per share (EPS), providing a common basis for comparing forecast assumptions. We evaluate six models under a common harness, assessing point forecast error relative to date-matched analyst consensus and checking whether their prediction intervals achieve the stated coverage. Three models show no detectable paired difference in point forecast error from consensus, and three have higher error. Across all six models, nominal 80% intervals contain reported EPS in only 37--70% of runs that return an interval, and most misses fall above the upper bound because the forecasts run low. The driver records trace most of the error gap between models to operating-income estimates.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.13745

Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth

Tianhao Niu, Qingfu Zhu, Wanxiang Che

原文摘要

Vision-language models (VLMs) can answer chart questions accurately, but output accuracy alone provides limited insight into the internal representations supporting exact value reading. We study value reading from vertical bar charts through controlled counterfactual activation patching in Qwen2.5-VL-7B-Instruct and InternVL3.5-8B. Our study connects three analyses. First, under one-tick bar-height counterfactuals, patching states selected by the changed-height region produces greater restoration of the original answer preference than patching states selected by the invariant bar body. Across language-model depth, restoration from legend- and series-related positions declines earlier than restoration from bar-geometry and axis-scale positions. Second, we identify middle-layer states at series-related prompt positions that can restore answer preference under legend swaps. Resetting these states selectively weakens restoration from an earlier visual-legend patch, demonstrating their causal role in the downstream effects of that intervention. Third, a factorial analysis shows that both models can combine geometry and scale states from separate donors to favor the combined target answer. Together, these results provide causal evidence about the internal states supporting exact bar-value reading.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.00442

Learning to Model Optimization Problems from Solver Outcomes

Runda Guan, Xiangqing Shen, Jiajun Zhang, Yifan Zhang, Jian Cheng, Rui Xia

原文摘要

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency or fine-tune smaller LLMs using costly process supervision that often overfits to a single solver API. We study how reinforcement learning from inexpensive outcome labels can improve optimization modeling and support reuse across heterogeneous solver environments. To this end, we propose Optimization Modeling from Solver Outcomes (OMSO), which uses reinforcement learning (RL) with a mathematical programming solver as a deterministic, interactive environment. Given a natural-language problem and a target solver, OMSO generates solver-specific code, executes it in a sandboxed harness, and converts execution outcomes into scalar rewards in a closed-loop generate-execute-feedback-update process. This RL formulation learns optimization modeling without process-level supervision and supports cross-solver generalization by switching the solver environment rather than reconstructing solver-specific datasets. Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that OMSO matches or outperforms process-supervised SFT, supports zero-shot training-free transfer, direct RL training, and SFT-cold-started RL, and improves modeling reasoning and semantic correctness beyond solver API usage.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38282

Human Evaluation with Automatic Scores: Separating Sampling and Estimation Gains

Yang Liu, Ran Zou, Zhengtao Gui, Chao Xue

原文摘要

Automatic judges offer inexpensive information about model outputs, but an evaluation team must decide how to turn that information into fewer human annotations. Scores can guide sampling, correct an estimate, or support adaptive acquisition, and these uses may capture overlapping gains. We compare their incremental value on fixed evaluation pools from three preference datasets, and 19 attributed-question-answering systems. Matched comparisons use the same scores, account for pilot labels and budget rules, and separate acquisition from estimation. Score stratification is a strong reference: after ten-bin stratification, the best fixed local linear correction offers only 1.00--5.27% further MSE reduction in the primary configurations. Unequal allocation offers larger gains in some pools, but can increase error when confident scores conceal variable human outcomes. Comparison on AttributedQA, shrinking learned quotas toward score-only quotas lowers pooled MSE for 17 of 19 systems relative to the score-only procedure, but ordinary pooled 95% intervals cover only 88.09--93.54%. The same shrinkage improves on the score-only reference in only one of eight preference configurations. Ranking experiments further show that lower individual MSE need not improve system selection. These findings support a simple starting procedure, proportional sampling within score strata followed by a stratified human mean, and identify what additional evidence is needed to justify correction or adaptation for the intended evaluation output.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2607.04726

What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

Tianhao Niu, Qingfu Zhu, Wanxiang Che

原文摘要

Chart-to-code generation is commonly trained through supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target. However, many chart programs contain latent variables that cannot be uniquely recovered from the rendered image. We identify this latent-observation mismatch in four forms across five chart types: aggregation-induced mismatch, where raw samples are reduced to box statistics or histogram bin masses; normalization-induced mismatch, where absolute scale is removed in pie charts; projection-induced mismatch, where 3D information is lost through 2D rendering; and level-set-induced mismatch, where a scalar field is observable only through selected contour lines. These mismatches introduce target ambiguity and require models to generate information unsupported by the image. We propose Observation-Aligned Supervision, which replaces latent variables with visually constrained quantities. And we study fixed-view 3D scatter and contour charts through controlled experiments. Across VLMs, observation-aligned supervision generally improves observable recovery end-to-end and under both-executable evaluation. Against compact analytic contour formulas, end-to-end performance declines despite better conditional boundary recovery in both-exec setting, suggesting a trade-off with representational compactness.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38267

Cross Lingual Abstractive Summarization for Marathi

Asang Dani, Shailesh R Sathe

原文摘要

Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization, both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages. Recent advances in Transformer architectures, pretrained language models (PLMs), and dataset availability offer new opportunities to address this gap. In this work, we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2, an Indic neural machine translation model. We evaluate the resulting models using ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction. Our experiments demonstrate that leveraging a pretrained translation model yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.22133

Observational Equivalence of LLM and Human Annotation

Kentaro Nakamura, Jing Ling Tan, George Yean

原文摘要

In this paper, we show that humans and large language models (LLMs) are observationally equivalent in coding texts. Recent LLMs agree with attentive humans at rates comparable to those observed among humans, and cross-LLM disagreement concentrates on texts that also divide humans. We demonstrate these patterns through replications of text-classification tasks from 14 peer-reviewed political science studies, with 13 LLMs, three human coders (Ph.D. students), and 165 crowd coders, independently applying identical codebooks. We further find that clarifying an underspecified codebook increases agreement among humans and between humans and LLMs. Together, these findings point to ambiguity in texts and coding rules as a shared source of disagreement and challenge the presumption that human labels should take precedence whenever humans and LLMs differ. We therefore argue that the central challenge of text annotation is not simply choosing between humans and LLMs, but developing coding rules that minimize ambiguity and accounting for the ambiguity that remains. To this end, we propose using cross-LLM disagreement to identify difficult cases, guide human review, and refine codebooks, and we develop ambiguity-aware bounds for downstream inference without requiring ground truth for every text.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.03672

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Chen Zhang, Kepu Zhang, Jiatong Zhang, Xiao Zhang, Jun Xu

原文摘要

Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) reasoning improves accuracy but incurs prohibitive latency for real-time query correction. A potential solution is to output an answer before reasoning to reduce latency; however, under autoregressive decoding, the early answer is independent of subsequent reasoning, preventing the model from leveraging its reasoning capability to improve accuracy. To address this issue, we propose Sandwich Reasoning (SandwichR), a novel approach that explicitly aligns a fast initial answer with post-hoc reasoning, enabling low-latency query correction without sacrificing reasoning-aware accuracy. SandwichR follows an Answer-Reasoning-Answer paradigm, producing an initial correction, an explicit reasoning process, and a final refined correction. To align the initial answer with post-reasoning insights, we design a consistency-aware reinforcement learning (RL) strategy: a dedicated consistency reward enforces alignment between the initial and final corrections, while margin-based rejection sampling prioritizes borderline samples where reasoning drives the most impactful corrective gains. Additionally, we construct a high-quality query correction dataset, addressing the lack of specialized benchmarks for complex query correction. Experimental results demonstrate that SandwichR achieves SOTA accuracy comparable to standard CoT while delivering a 40-70% latency reduction, resolving the latency-accuracy trade-off in online search.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38231

3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing

Binjie Wang, Xinran Zhao, Shoubin Yu, Xiang Li, Silong Yong, Chenyang Yang, Tianyu Chen, Ruofei Du 等 11 位作者

原文摘要

Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such edits require understanding what a program builds and foreseeing how a change reshapes it, yet prior benchmarks mostly evaluate generation or simple edits against a reference. In this paper, we introduce 3DCodeEdit, a benchmark of 2,592 instruction-guided editing tasks over 108 Blender programs that construct objects entirely in code. Its edits range from parameter to structural changes, style redesign, and scene composition, and are judged from renders against human-reviewed checklists. Across 17 models, the average success rate is only 37%, and even the strongest models complete fewer than 60% of structural and style edits. As models become more capable, their failures shift to geometric foresight, where the code runs but builds the wrong shape. We therefore study whether multi-turn feedback can compensate for this missing foresight. Feedback from a separate reviewer model that describes how the renders differ from the request helps most, more than maximum reasoning effort or an agent harness, and can let a 27B model surpass the single-shot rate of a 2.8T-parameter model.

cs.CL · cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30518

Protegrity-PII Technical Report

Hardeep Bassi, Hui Ma, Luís Seabra, Koowum Joshi, Daniel Pereira, Averell Gatton

原文摘要

We present Protegrity-PII, a new PII detection model for structured and unstructured text. Protegrity-PII achieves a typed recall of 0.910 with a precision of 0.902 on a new benchmark we propose, PII-SCOPE. Our model processes text in 0.49 seconds per million characters at \$0.0005 per million characters on a single RTX 6000 using batched inference. Due in part to the expansive nature of the entity type taxonomy used in training, Protegrity-PII achieves superior out-of-distribution generalization when benchmarked against a selection of state of the art models and datasets.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38204

Two Birds with One Stone: Skill-Augmented Generation via Unified Retrieval and Utilization

Zihan Luo, Jiahui Kang, Wei Zhou, Qilin Fan, Mingyan Li, Chao Chen

原文摘要

Skills, as reusable external knowledge, have demonstrated substantial potential to enhance the ability of Large Language Models (LLMs) to solve complex tasks. However, existing skill-augmented generation methods typically rely on separate models for skill retrieval and skill utilization, resulting in disconnected optimization of these two processes. To address this gap, we propose Skill-Uni, a unified reinforcement learning framework that jointly optimizes skill retrieval and utilization. Specifically, we adopt a generative skill retrieval paradigm that enables a single model to both learn how to retrieve relevant skills and leverage them for task solving. To effectively train this unified framework, we introduce a two-stage training strategy consisting of warm-up instruction tuning and GRPO, allowing the model to progressively improve its skill retrieval and utilization capabilities. Extensive experiments on five skill-related benchmarks demonstrate the effectiveness of Skill-Uni, yielding average performance gains of 66.59% and 34.82% over the base Qwen3-4B and LLaMA3.1-8B models, respectively. Besides, Skill-Uni is compatible with various skill retrieval engines, demonstrating its flexibility and generalizability. Additional in-depth analyses also provide insights into the effectiveness of Skill-Uni.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36554

PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy

Vansh Bhatia, Mehdi Rezagholizadeh, Parsa Ashrafi Fashi, Igor Gilitschenski, Vikram Appia, Emad Barsoum

原文摘要

Final-answer accuracy reports whether a vision-language model was right, but not whether its answer was grounded in the image, whether its stated reasoning reflects that evidence, or what the answer cost to produce. Those are the properties that decide whether a system can be deployed. We present PRISM-BENCH, a benchmark of 1,000 expert-curated questions spanning five under-represented reasoning categories, in which every item carries an idealized reasoning trace written by one human annotator and validated by another. The traces support two diagnostics that accuracy cannot provide. A perception probe, in which the model answers from a description it wrote itself, attributes roughly 85% of frontier-model failures to misperception and places the bottleneck at grounding. Trace alignment predicts answer correctness for all 25 systems tested (macro AUROC 0.66) and survives length control, so it measures reasoning content and not verbosity. We further introduce CORE, an efficiency-aware metric that reorders 24.2% of model pairs relative to accuracy while remaining uncorrelated with response length. Across 25 open and closed systems, including GPT-5 and Claude Opus 4.6, the best accuracy is 66.0%. On the four categories with a human baseline the best system trails humans by 18.4 points, and recent frontier gains fall on recognition and not on spatial grounding.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38181

Component Translation and Judge-Labelled Refusal: A Multilingual Safety Evaluation

Yongxi Zhou, Junwei Yao, Wenbo Ye, Jiahui Ge

原文摘要

Whole-prompt translation evaluates a request in different languages but does not compare which component carries a language. We introduce a paired reversal: translate the complete request component or the complete operation component into the same target language, holding behaviour, English frame and translated-span count fixed. Component identity and non-English text quantity change together. Assigning English, Chinese and Spanish independently to the two components yields nine configurations on 190 of 300 sampled harmful behaviours retained after consensus annotation and automatic gating. Refusal scored by language-model judges is the primary outcome; unsafe compliance is reported separately. On Gemini 2.5 Flash and DeepSeek, three refusal swaps are about 5.3 percentage points and the fourth is -0.5; none survives the pre-specified six-test Holm correction. In an exploratory extension, Mistral Small 4 has a 13.7-point Spanish swap (95% interval [8.4, 18.9]), which survives the twelve-test Holm sensitivity correction under the primary judge, and 12.1 points under a second judge. GPT-5.4-mini estimates are within 2 points of zero. Component assignment supplies an additional evaluation dimension. Evaluations should record component languages and translated text quantity, comparing matched behaviours at equal translated-span count while interpreting refusal and unsafe compliance separately.

cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38174HF 社区推荐

Scaling Lean Theorem Proving for Real-World Code Verification

Debargha Ganguly, Divya Raghunathan, Dejan Jovanović, Vikash Singh, Soonho Kong, Aaron Tomb, Aman Goel, Ferhat Erata 等 9 位作者

原文摘要

We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration service. Using an off-the-shelf frontier model with no additional training, it proves 669/672 PutnamBench problems and all six IMO 2026 formalizations and resolves 597/600 NTP4VC verification conditions and all 189 VERINA tasks by proof or refutation. Because these benchmarks are close to saturation, we also introduce Aegis, which converts competitive programming problems into much harder verification tasks over real implementations. The pipeline writes safe Rust solutions, translates them into Lean with Aeneas, generates specifications, and labels each frozen statement with a kernel-checked proof or refutation. It produces 2,045 differentially validated Rust-Lean program pairs and 11,533 candidate specifications. Unlike hand-written benchmarks, these tasks carry implementation-level obligations from fixed-width arithmetic, explicit failure, generated loops, casts, and functionalized mutation. On a stratified sample of 2,000 statements, EasyProver proves 1,054 (52.7%) within a 30-minute budget per statement. The same tasks can also be used to benchmark other provers and as rewards for reinforcement learning.

cs.CL · cs.AI · cs.LO · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38160

ATI-OPD: Adaptive Teacher Intervention for Stable Long-Sequence On-Policy Distillation

Jiannan Guan, Youxin Jiang, Yutai Hou, Qiguang Chen, Yirong Zeng, Haitao Wang, Dengyun Peng, Zheng Yan 等 12 位作者

原文摘要

On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own reasoning, weakening its feedback on later tokens. Updates based on this feedback can reinforce the same deviations in later responses and destabilize training. Prior approaches such as length control and loss reweighting limit learning from problematic responses but leave their prefixes unchanged. Fixed cutoffs can also discard later reasoning. We propose \textbf{Adaptive Teacher Intervention for On-Policy Distillation (ATI-OPD)} to improve subsequent teacher guidance by revising the student's reasoning prefix. ATI-OPD replaces the earliest high-disagreement segment with a short teacher segment, then lets the student resume its own reasoning from the revised text. To handle renewed disagreement, it excludes persistently divergent suffixes from the distillation loss while retaining useful student continuation. Training diagnostics show less teacher-student disagreement, fewer gradient spikes, and fewer extremely long responses. Across five mathematical reasoning benchmarks and two teacher-student pairs, ATI-OPD improves average student-only accuracy over standard OPD.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.02332

Forget Attention: Importance-Aware Attention Is All You Need

Suhyeong Shin, Yeongwook Yang

原文摘要

Attention retrieves content precisely, but its scores depend only on query--key products, leaving order and recency to positional encodings. Conversely, state-space models (SSMs) such as Mamba-3 track order and recency through input-dependent state transitions that decay and rotate, yet compressing context into a fixed-size state hampers precise retrieval. Hybrids like Samba and Hymba exploit this complementarity only across layers or heads, so SSM transitions never shape attention scores directly. The closest prior work, the Forgetting Transformer (FoX), adds an input-dependent forget gate to the scores but reweights attention by recency alone. We propose SSM-Informed Softmax Attention (SISA), which builds Mamba-3-style state transitions, rotation included, directly into the scores alongside FoX's gate. Each logit receives the weight such an SSM would give that token pair: a decayed match between rotated SSM projections. This rotation already encodes relative position, so SISA drops RoPE; restoring it raises loss. SISA outperforms parameter-matched Transformer and FoX in language modeling and length extrapolation. Among the attention models we compare, hybrids included, only SISA benefits from context beyond the training window. Building SSM transitions into the scores yields stronger attention, and our kernels make it faster and leaner than baselines on their official or standard kernels.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38096

Calculation and rejection diverge in language models tested at known mechanical limits

Shaoliang Yang, Jun Wang

原文摘要

When a language model returns engineering quantities with the status "solved", software that trusts it passes them on, even when the requested design is physically impossible. Such failures could reflect poor calculation, how the answer is requested, or a failure to judge feasibility. We set beam loads and disk speeds at known percentages above or below plastic collapse or burst, measured each model's limit calculation separately and tested 12 models in 4,860 calls, including follow-up experiments on new designs. We find that a model can recognize an impossible design when asked only whether it is feasible, yet accept the same design, reporting "solved", when asked for a full answer. Three models accepted beams 10 to 30% beyond collapse despite precise limit calculations in separate questions, and many accepted replies stated the violation. Asked only about feasibility, Opus 5 and Gemini 3.8 Flash rejected every impossible new design they were given, including those accepted in full answers, without false alarms. Rewording when to decline or changing the answer format raised rejection on the original beams, but not consistently on new designs. Software and benchmarks using a model's status should test feasibility judgment and full-answer rejection separately, and report the exact prompt.

cs.CE · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38095

Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI

NVIDIA, :, Aastha Jhunjhunwala, Aayushi Ashokkumar Srivastava, Abhibha Gupta, Abhinav Garg, Abhinav Khattar, Achsah Wildish 等 559 位作者

原文摘要

We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.30076

Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects

Hongyu Yu, Yifei Shen

原文摘要

Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.

cs.CL

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1软件学报:jos:7743软件学报

人工智能保险箍: 发展现状与未来展望

李金海, 李若涵, 胥迤潇, 李默涵, 孙彦斌, 田志宏, 方滨兴

原文摘要

近年来, 以大语言模型和具身智能为代表的面向通用人工智能发展的相关技术快速演进, 其广泛应用在带来巨大潜力的同时, 也引入了复杂的安全风险. 这些风险总体可分为两类: 一类是源于模型缺陷、系统设计或环境不确定性的自发性风险, 另一类是由外部对抗攻击或恶意诱导触发的诱发性风险. 为保障人工智能系统在开放环境中的安全可靠运行, 人工智能保险箍通过风险感知、风险量化与风险熔断这3类核心能力, 为人工智能行为体构建独立的安全保障机制, 使系统具备在行为偏离安全边界时及时识别、风险评估与干预控制的能力. 以人工智能保险箍为研究对象, 系统梳理相关研究进展与关键技术. 首先界定人工智能行为体的基本概念及其潜在失控风险类型. 随后围绕风险感知、风险量化与风险熔断这3个技术维度, 对相关研究进行系统分类与综述, 并分析国内外代表性工作的研究现状. 区别于以威胁检测或单点防御技术为核心的综述, 从构建面向人工智能行为体的底线安全机制这一视角出发, 对人工智能保险箍的技术体系进行整体分析. 最后讨论该领域面临的关键挑战与未来发展方向, 为构建安全可控的人工智能系统提供参考.

cs.* · cs.CL · cs.AI

软件学报 · 2026 · 正式发表

查看论文
软件学报 ↗PDF ↗
新论文 · v1arXiv:2610.38067

From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA

Aria Nourbakhsh, Adelaide Danilov, Oleksandr Marchenko Breneur, Salima Lamsiyah

原文摘要

Sparse autoencoders (SAEs) can predict internal features associated with model errors, but association alone does not establish causal influence. We study this distinction in multiple-choice question answering, where answer preference can be measured by the logit margin between the correct answer and the competing choices. Across eight datasets, we analyze Gemma~3 1B and 4B with Gemma Scope SAEs. We propose a pipeline to filter out the features that have high correlation with format and content artifacts, such as prompt and answer permutation, and evaluate the remaining ones with causal feature interventions. Our results show that SAE activations contain predictive signals about wrongness and uncertainty across models and datasets. After filtering artifact-contaminated features, selected features for causal intervention at question and option spans produce larger absolute margin shifts and a higher wrong-to-correct rate than randomly selected features, indicating greater causal leverage. However, answer flips are rare, and we do not observe stable effect directions across meaning-preserving changes in prompt format and answer order. An adapted HalluSAE baseline produces larger final-token margin changes, but relies on substantially contaminated features and does not significantly improve correction rates. Therefore, the identified features reflect context-dependent answer competition rather than the mechanism of incorrect answer errors.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.17843

Decodable but Not Actionable: Auditing the Representation-Behavior Gap in Frozen LLMs for Geometric Constraints

Man Liang, Xinzhao Cheng, Faizan Wajid

原文摘要

Large language models (LLMs) perform well on structured reasoning tasks, but what they encode and whether encoded information guides their behavior remain unclear. We introduce a controlled auditing framework that uses parametric CAD to distinguish failures of encoding, expression, and activation-level control. Applied to eight pretrained models and matched randomly initialized controls, our framework reveals that pretraining contributes substantially more to linear decoding of local relations than to global constraint status, which is already highly decodable from random representations. Yet strong local decodability does not translate into the models' zero-shot predictions, which remain far below supervised probe performance. Restoring clean internal activations can repair probe predictions, whereas simple activation steering does not provide reliable targeted control. With only 400 labeled relation pairs, low-rank fine-tuning substantially improves generation on three representative models, showing that the representation--behavior gap can be reduced through adaptation. Together, these findings show why decodability alone is insufficient evidence that encoded information will be expressed or controllable in model behavior.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38041

CARF: Context-Aware Reasoning Supervision for Scientific Evidence Screening

Nishtha Agarwal, Adam Visokay, Astha Wahi, Kwabena Owusu Aninkora, Amy Gu, Tyler McCormick, Li Liu

原文摘要

Systematic reviews synthesize biomedical evidence to inform clinical and public-health decision-making, but require domain experts to manually screen thousands of studies against detailed eligibility criteria. We investigate whether language models can assist with this bottleneck by learning from expert feedback on title and abstract screening decisions and model-generated reasoning. We introduce the Context-Aware Reasoning Framework (CARF), a human-in-the-loop framework that uses expert feedback on model-generated reasoning to adapt language models to context-dependent screening tasks. We evaluate CARF on systematic reviews of verbal autopsy and cause-of-death ascertainment methods used in global public health mortality surveillance. CARF shows competitive screening performance compared to evaluated models while retaining high sensitivity, and is more inclined to retain ambiguous, context-dependent studies for human review. Together, these findings suggest that expert-corrected reasoning is a promising supervision signal for context-dependent scientific screening, while retaining a role for human oversight.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38016

Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms

Olga Kellert, Samhitha Harish, Johnatan E Bonilla, Nemika Tyagi, Phanos Kareen, Nelvin Licona-Guevara

原文摘要

Automatic speech recognition (ASR) increasingly supplies transcripts for educational NLP, but aggregate word error rate (WER) can conceal errors concentrated in learner speech, multilingual turns, and speaker attribution. We compare platform-integrated, open-weight, adapted, and commercial ASR configurations on held-out sessions of online L2 Spanish interaction between L1 English learners and their instructors and tutors. Because English is the learner's shared first language, the interactions contain Spanish-only, English-only, and code-switched turns. Evaluation combines overall WER and character error rate (CER), WER disaggregated by speaker role and language context, and diarization error rate (DER). We also adapt Whisper large-v3 and MOSS-Transcribe-Diarize with LoRA using human-corrected in-domain classroom data. MOSS adaptation produced consistent improvements across speaker roles and language contexts, whereas Whisper showed smaller gains. Domain match proved more important than data volume: Larger out-of-domain bilingual and learner corpora did not outperform the smaller classroom corpus, where learner speech and code-switching are embedded in instructor--learner interaction. The open-weight MOSS adapter was competitive with commercial Muse Voice Transcribe on WER and CER and achieved lower system-provided DER on the recordings eligible for each system. Learner, English-only, and code-switched speech remained more difficult than instructor and Spanish-only speech. The findings demonstrate the value of condition-aware evaluation and interactionally matched data for bilingual educational ASR.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38015

Measured or Real? When Model-Derived Measurements Can Be Corrected or Compared

Yifeng Li, Ziang Ni

原文摘要

Numbers computed from trained models, such as an example's difficulty or a model's benchmark lead, change with seed and prompt. We ask when such measurements can be corrected or compared. Noise shrinks correlations, and the textbook correction divides by the square root of two estimated reliabilities. On two CIFAR-100 difficulty scores, it returned correlations above one in 70 of 100 classes. We prove that its mean squared error is infinite even when the correlation and the reliabilities use separate seeds. Our rule corrects only when both reliabilities pass a significance test, then divides by their upper confidence bounds. Its output is always bounded, and its coverage guarantees assume Gaussian noise. It helps once reliability is well estimated, more than halving the error with 500 simulated units. Prompt settings can reverse rankings. On ARC, Qwen2-1.5B trails Llama-3.2-3B by 3.8 points with no examples in the prompt and leads by 16.6 with two. Across four benchmarks, averaging the two settings names one winner for 15 of 16 such reversals. We compare models within each setting, controlling family-wise error asymptotically in the number of items for a fixed prompt grid. Aligning embedding coordinates across seeds raises held-out per-dimension reliability from 0.003 to 0.813.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38009

Large Language Models for Accurate Medical Chart Abstraction: Enabling Scalable and Secure Artificial Intelligence Deployment in Stroke

Zhusi Zhong, Carl M. Porto, David Hong, Miranda Gonzales, Revyn Kim, Gnaneswari Karayi, Lulu Bi, Joshua R. Feler 等 16 位作者

原文摘要

Medical chart abstraction transforms unstructured clinical narratives into structured variables for research and quality monitoring. We evaluated a prompting-based large language model (LLM) framework for extracting eight clinical variables from 2,416 neurointerventional acute stroke intervention reports across three hospitals. Twenty-two instruction-tuned open-source LLMs were evaluated across architectures, model sizes, and biomedical adaptations using Quick Response and Chain-of-Thought (CoT) prompting. Non-expert staff annotations served as the cross-model reference standard. Evaluation was restricted to report-variable pairs with a valid LLaMA3.3-70B CoT prediction and a corresponding reference label. Performance measures included extraction accuracy, inference latency, and agreement with expert adjudication. Twenty discordant cases per variable underwent review by two senior physicians and four medical students. LLaMA3.3-70B achieved the highest overall accuracy (94.8%). CoT improved performance on inference-dependent variables such as site of occlusion, while Quick Response was optimal for directly stated procedural fields. Expert adjudication showed that AI predictions were more closely aligned with expert interpretations than non-expert annotations for most variables, with intracranial angioplasty remaining a challenge. Locally deployed LLMs can support scalable clinical information extraction and retrospective stroke registry curation, with expert oversight for ambiguous cases.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38005

"It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI

Dana Serditova, Kevin Tang, Jochen Steffens

原文摘要

Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations and how regional voices produced by voice assistants (VAs) are evaluated through a sociolinguistic lens. This study investigates these issues among speakers of Newcastle English (Geordies), examining both linguistic accommodation to voice technologies and perceptions of regional versus mainstream-accented VA voices. Participants interacted with a simulated VA that spoke either Newcastle English or Standard Southern British English (SSBE). They subsequently completed semi-structured interviews about their experiences with the experimental VA and voice technologies, language use, accent attitudes, and place orientation. The findings reveal a two-way process of sociolinguistic bias. The Geordie VA was associated with familiarity, warmth, personality, and local belonging, but also with concerns about professionalism and authority, whereas the SSBE voice was perceived as more neutral, clear, and credible. Participants also reported adapting their speech when voice technologies failed to recognise them, most commonly by shifting to a more mainstream accent, enunciating more clearly, and speaking more slowly. These strategies are similar to accommodation in human-human interaction and reflect users' perceptions of what technologies can recognise, also known as perceived intelligibility pressures. Overall, the findings demonstrate that voice technologies can reproduce existing accent biases both by encouraging users to suppress regional features and by activating established social stereotypes through synthetic voices. The study positions sociolinguistics as a bridge between understanding human-AI interaction and designing inclusive technologies around users' own linguistic priorities.

cs.HC · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2601.16407

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attribution

Toni J. B. Liu, Baran Zadeoğlu, Gurbir Arora, Raphaël Sarfati, Nicolas Boullé, Christopher J. Earls

原文摘要

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token level causal attribution methods for interpreting LLM predictions. Grounded in perturbation theory and information geometry, Jacobian Scopes quantify how input tokens influence various aspects of a model's prediction, such as specific logits, the full predictive distribution, and model uncertainty (effective temperature). Through case studies spanning instruction understanding, translation, and in-context learning (ICL), we demonstrate how Jacobian Scopes reveal implicit political biases, uncover word- and phrase-level translation strategies, and shed light on recently debated mechanisms underlying in-context time-series forecasting. On token-ablation faithfulness benchmarks (LAMBADA and IWSLT2017) across six LLMs, the distribution-level Fisher and Temperature Scopes significantly outperform established gradient-based attribution methods in 10 of 12 model-dataset settings. To facilitate exploration of Jacobian Scopes on custom text, we open-source our implementations and provide a cloud-hosted interactive demo at https://huggingface.co/spaces/Typony/JacobianScopes.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37995

QMUL_AK at AISA-ArabicFC: Schema-Constrained Function Calling with ALLaM

Ali Khairallah, Arkaitz Zubiaga

原文摘要

We describe the QMUL_AK submission to AISA-ArabicFC 2026. The system adapts the Arabic-English ALLaM-7B-Instruct model to function calling with low-rank adaptation (LoRA). It combines an Arabic schema-aware prompt, dialect and no-call resampling, a token-weighted training objective, and deterministic validation of generated calls against the candidate tool schema. The same output supports Track A function calling and Track B reasoning-augmented calling. Training uses only the official task data. On the development set, the system achieves 0.9982 function accuracy and 0.8920 argument exact match, corresponding to overall A and B scores of 0.9345 and 0.9454. On the blind test set, the system reaches overall A and B scores of 0.9253 and 0.9380, ranking 3rd on both submission tracks and 1st of 21 teams on the Track C dialect-robustness diagnostic with a macro-averaged score of 0.9075 and the smallest dialect gap in the shared task (0.077). The results show that function selection is nearly saturated, while argument extraction remains the main source of error.

cs.CL

查看论文
arXiv ↗PDF ↗