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 17:16 — 2026-11-09 17:16（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 18,172 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）
新论文 · v1arXiv:2610.37267

GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search

Zhiheng Fu, Zixu Li, Zhiwei Chen, Jiale Huang, Fangxu Liu, Jinhe Bi, Yupeng Hu

原文摘要

Text-based Person Anomaly Search (TPAS) retrieves a target pedestrian using natural-language descriptions of appearance and normal or anomalous behavior. Unlike conventional text-based person retrieval, TPAS must preserve identity cues while distinguishing fine-grained behaviors. It presents two challenges: same-identity, different-behavior hard negatives cause gradient conflict during granular alignment, while strong appearance cues can obscure weak behavioral evidence during aggregation. We propose GradCO (behavior-aware Gradient-Conflict Offloading), comprising three complementary components. Behavior-Aware Mixture-of-Experts (B-MoE) forms appearance, normal-behavior, and anomalous-behavior streams whose roles are learned from retrieval objectives without expert-specific semantic labels. Conflict Offload Learning (COL) uses pair-conditioned offload anchors in similarity computation to reduce the conflicting-gradient burden on the main text representations. Hierarchical Intent Alignment (HIA) aggregates expert similarities and features using query-conditioned weights. Experiments on five TPAS/TIPR benchmarks show GradCO significantly surpasses SOTA methods and validate our design.

cs.CV · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37266

Watermark Basins: Black-Box Detection of Distilled LLMs

Hongyan Chang, Hady Elsahar, Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Sylvestre-Alvise Rebuffi, Tomáš Souček, Tuan Tran 等 13 位作者

原文摘要

Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of distillation, model providers can watermark the teacher's outputs, aiming to leave a radioactive signal in the student's outputs. Existing black-box detectors search for such radioactivity using token-level statistics of the suspect model's outputs. However, token-level signals are not always detectable, for instance when the distillation traces are sampled at a low temperature. In this work, we discover the watermark basin, a persistent signal that enables more reliable watermark detection: during fine-tuning, watermarked teacher traces embed a distinct, key-specific geometric signal in parameter space that lies orthogonal to the ordinary task-specific fine-tuning subspace. Building on this, we introduce Watermark Basin Alignment (WM-Basin), a black-box watermark detector that queries the suspect model through its API, without access to its weights or logits. WM-Basin maps generated text to gradient representations using a fixed clean probe model, projects out the ordinary fine-tuning task directions, and tests whether the residual gradient aligns with the watermark basin induced by the watermark key. We evaluate WM-Basin extensively across diverse teacher models and student architectures (from 135M to 8.2B parameters) distilled on mathematical reasoning. At a strict 0.1% false-positive rate, WM-Basin detects 79% of distilled models at n-gram=1 and 45% at n-gram=3, substantially improving over the state-of-the-art token-level baseline (29% and 1.3%, respectively). Because the watermark signal resides in a persistent basin, it survives post-distillation modifications including quantization, pruning, and reinforcement-learning post-training.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37265

REGLAT at ArGuard Shared Tasks: An Ensemble-Based Model Integrating NER for Harmful Content Detection in Arabic

Ahmed M. Fetouh, Mariam Labib, Nsrin Ashraf, Omer Dawood, Hamada Nayel

原文摘要

Detecting harmful content in Arabic is challenging because of dialectal variations and the semantic overlap between different harm categories. This paper presents a two-stage approach for classifying Arabic user prompts into seven categories of harmful content. First, GLiNER is used to extract harm-related entities from each prompt. The extracted entities are then added to the original text and passed to a fine-tuned MARBERT classifier for final classification. The approach combines explicit entity information with the contextual understanding of a pretrained Arabic language model. The system was evaluated on the development set of the ArGuard 2026 shared task. The results achieved a macro-F1 score of 0.886 and an accuracy of 0.897, demonstrating promising performance in fine-grained harmful content detection. The system reported an accuracy of 0.793 and Macro-F score of 0.735 on a blind test set for subtask 1. For subtask 2, it achieved an accuracy of 0.770 and Macro-F score of 0.754. The analysis also showed that distinguishing between related categories remains challenging. These findings suggest that integrating NER with Arabic language models is a promising approach to harmful content detection.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2407.04898

Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning

Joon Suk Huh, Kirthevasan Kandasamy

原文摘要

We study a multi-round mechanism design problem, where we interact with a set of agents over a sequence of rounds. We wish to design an incentive-compatible (IC) online learning scheme to maximize an application-specific objective within a given class of mechanisms, without prior knowledge of the agents' type distributions. Even if each mechanism in this class is IC in a single round, if an algorithm naively chooses from this class on each round, the entire learning process may not be IC against non-myopic buyers who appear over multiple rounds. On each round, our method randomly chooses between the recommendation of a weakly differentially private online learning algorithm (e.g., Hedge), and a commitment mechanism which penalizes non-truthful behavior. Our method is IC and achieves $O(T^{\frac{1+h}{2}})$ regret for the application-specific objective in an adversarial setting, where $h$ quantifies the long-sightedness of the agents. When compared to prior work, our approach is conceptually simpler,it applies to general mechanism design problems (beyond auctions), and its regret scales gracefully with the size of the mechanism class.

cs.GT · cs.CR · cs.DS · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.09813

Prismatoid Band-Unfolding Revisited

Joseph O'Rourke

原文摘要

It remains unknown if every prismatoid has a nonoverlapping edge-unfolding, a special case of the long-unsolved "Dürer's problem." Recently nested prismatoids have been settled [Rad24] by mixing (in some sense) the two natural unfoldings, petal-unfolding and band-unfolding. Band-unfolding fails due to a specific counterexample [O'R13b]. The main contribution of this paper is a characterization when a band-unfolding of a nested prismatoid does in fact result in a nonoverlapping unfolding. In particular, we show that the mentioned counterexample is in a sense the only possible counterexample. Although this result does not expand the class of shapes known to have an edge-unfolding, its proof expands our understanding in several ways, developing tools that may help resolve the non-nested case.

cs.CG · math.MG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37256

Fast Approximate Line Nearest Neighbor Search

Jiadong Xie, Jeffrey Xu Yu, Yingfan Liu

原文摘要

Approximate nearest neighbor (ANN) search, which retrieves vectors close to a given query vector, is a fundamental operation in vector databases. However, emerging applications, such as selecting source images for photo-based animation and video synthesis, may require matching content while allowing a query-specified aspect contrast, such as an illumination change, to vary; a single query point does not directly express this requirement. In this paper, we study approximate line nearest neighbor (LANN) search, where an infinite query line removes the distance contribution along a specified direction while database records remain points. Prior approaches focus on top-$1$ search only for LANN and can incur high construction costs. Converting LANN into ordinary point ANN search through dimension lifting substantially increases index construction and query costs, while direct search on a proximity graph built for ordinary point ANN search can miss distinct regions close to a line. To address these issues, we propose LinePG, which enhances an existing proximity graph with pair edges to facilitate navigation between separated near-line regions. To find these pair edges efficiently, we first generate region pairs with spatial or graph separation, and near a line. We then score edges between the selected region pairs to guide the point endpoint selections. We conduct extensive performance studies and confirm the accuracy and efficiency of LinePG in comparison with the baseline approaches.

cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.06993

Optimal Experiments for Partial Causal Effect Identification

Tobias Maringgele, Jalal Etesami

原文摘要

Causal queries are often only partially identifiable from observational data, and experiments that could tighten the resulting bounds are typically costly. We study the problem of selecting, prior to observing experimental outcomes, a cost-constrained subset of experiments that maximally tightens bounds on a target query. We formalize this as the max-potency problem, where epistemic potency measures the worst-case reduction in bound width guaranteed by an experiment, and show that this problem is NP-hard via a reduction from 0-1 knapsack. Building on the polynomial-programming framework of Duarte et al. (2023), we give a general procedure for evaluating epistemic potency in discrete settings. To control the super-exponential search space, we introduce two graphical pruning criteria that depend only on the causal graph and the query: a novel path-interception rule that exploits district structure to certify zero potency in linear time, and an identifiability check based on the ID algorithm. On Erdos-Renyi random graphs and 11 bnlearn benchmark networks, the two criteria together prune 50-88% of candidate experiments on average without solving a single polynomial program. For the general subset search, we show that ID-pruned experiments are combinatorially inert, yielding a super-exponential reduction in the number of subsets evaluated. We close with an end-to-end demonstration on observational NHANES data, selecting optimal experiments for estimating the effect of physical activity on diabetes.

cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23364

Power of Conditional Sampling on Hypergraphs

Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Gopinath Mishra

原文摘要

Let $G=(V,E)$ be a $d$-uniform hypergraph with $|V|=n$ and $|E|=m$. Estimating $m$ from uniformly random hyperedge samples requires $Θ(\sqrt{m})$ samples by a birthday-paradox argument. We investigate the power of conditional sampling through a hierarchy of oracles: for an integer $1\le s\le d$, given pairwise disjoint subsets $X_1,\ldots,X_s\subseteq V$, the $s$-colorful oracle returns a hyperedge chosen uniformly at random from all hyperedges contained in $X_1\cup\cdots\cup X_s$ that intersect every $X_i$, provided one exists. For $s=1$, this samples a uniformly random hyperedge induced by $X_1$. For every $1\le s\le d$, we give a randomized algorithm that outputs $\widehat{m}\in[(1-\varepsilon)m,(1+\varepsilon)m]$ with probability at least $2/3$ using $O_{s,d}(\operatorname{poly}(1/\varepsilon,\log n))$ conditional samples, where the exponent of $\log n$ is an absolute constant independent of both $s$ and $d$. Conditional sampling thus yields an exponential separation over uniform hyperedge sampling. We also study the decision version, in which the oracle only reports whether a qualifying hyperedge exists. For every $1\le s<d$, we prove that any algorithm using the $s$-colorful decision oracle requires $\widetildeΩ_{s,d}(n^{\frac{d-s}{d-s+1}})$ queries. Hence, for $s<d$, access to uniformly random witness hyperedges (random certificates) is exponentially more powerful than existence queries. For $s=d$, decision queries alone achieve $\operatorname{poly}(1/\varepsilon,\log n)$ query complexity, but the exponent of $\log n$ is known to be $Θ(d)$. The colorful hierarchy thus exhibits a phase transition at $s=d$: for $s<d$, random certificates are essential for polylogarithmic-query estimation, whereas at $s=d$ decision queries suffice, yet random certificates still provably reduce the exponent of $\log n$ from $Θ(d)$ to an absolute constant.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.16925

Comparing GenAI to Machine Learning and Manual Review for eDiscovery

Gordon V. Cormack, Maura R. Grossman

原文摘要

Keeling et al. [Keeling2026Generative] report on a case study recently conducted by Redgrave LLP in which they assert that Relativity's Generative AI Review tool (aiR) achieved 88% recall while Relativity Assisted Learning (RAL), its machine-learning tool, achieved 64% recall. These results are not comparable because the methods employed have different objectives, because of inter-assessor disagreement, and because they represent different recall-precision and cost-benefit trade-offs. Our analysis of the Redgrave data indicates that, when these differences are taken into account, aiR and manual review are comparable. Furthermore, established machine-learning models employing Continuous Active Learning (CAL) and Scalable Continuous Active Learning (S-CAL) show state-of-the-art effectiveness, and superior efficiency, when trained only on a sample of 2,000 first-pass-reviewer responsiveness determinations.

cs.LG · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.21536

It Takes Two Moments: Rigidity and Limits of Continuous Encoders for Over-the-Air Computation

Saeed Razavikia

原文摘要

We study over-the-air computation of functions, such as empirical variance, formed by combining two separately postprocessed sums of locally transformed observations. We consider continuous encoders subject to pointwise peak-power constraints over a single use of a complex multiple-access channel. With four or more transmitters, we identify conditions under which exact noiseless recovery forces every continuous encoder collection into a common affine structure that preserves both sums, reducing infinite-dimensional encoder design to selecting a finite set of coefficients. To quantify resilience against channel noise, we introduce a robustness score that measures the separation of noiseless received aggregates relative to variations in the desired function value. Within this characterized encoder family, we formulate robustness maximization as an exact convex semi-infinite program, eliminating rank constraints without a relaxation gap, and construct a decoder that attains the minimum uniform noise-amplification constant. For several function classes, including empirical variance, we derive closed-form robustness-optimal encoders and scores. Under mild regularity conditions, we also establish sharp limits on the Gaussian mean squared error at high signal-to-noise ratios and show how using the input distribution reduces average error at the expense of uniform robustness.

cs.IT · eess.SP · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.24585

Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language

Mathis Immertreu, Achim Schilling, Thomas Kinfe, Patrick Krauss

原文摘要

Neural language models are typically trained on next-token prediction, although linguistic structure spans multiple temporal scales. Successor representations (SRs) make this horizon explicit by encoding discounted distributions over future states. Here, we ask whether such predictive representations can recover not only word classes, but also finer functional and construction-like structure from natural language. A residual network trained on WikiText-103 predicts SR distributions at three horizons without part-of-speech supervision. At the shortest horizon, unsupervised clustering robustly recovers nouns, verbs, and adjectives, while directed inter-cluster transitions reproduce familiar syntactic asymmetries. At finer resolutions and across 13 part-of-speech categories, the same geometry reveals semantic-functional groupings that cross category boundaries and directed relations tracing candidate date, measurement, and title-name constructions. Part-of-speech agreement declines as the predictive horizon lengthens. These results suggest that word classes are coarse regions within a richer predictive geometry in which categorical and construction-like linguistic structure emerge from future-word distributions.

cs.CL · q-bio.NC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37245

Aligning Large Language Models for Safety in African Languages: A Case Study of Hausa

Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Paula Chikaodinaka Anyanwu, Danielle Blanche Kapsa, Saminu Mohammad Aliyu, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad

原文摘要

Safety alignment research for large language models (LLMs) remains concentrated on high-resource languages, leaving open how existing alignment methods perform in low-resource, culturally distinct settings. We study this question for Hausa, a language spoken by more than 200 million people across West Africa. We introduce HausaSafeLM, one of the first Hausa safety preference dataset, built from 10,000 prompts derived from PKU-SafeRLHF: 3,000 human-corrected (gold) and 7,000 machine-translated (silver) examples spanning six harm macro-categories. Using Qwen2.5-7B-Instruct, we compare supervised fine-tuning (SFT) and SFT followed by Direct Preference Optimization (DPO) under both data regimes, evaluating on 500 harmful and 200 benign Hausa prompts.We find that the untuned base model appears highly safe by refusal-rate metrics alone, but this reflects limited Hausa generation ability rather than genuine alignment: its refusals are almost uniformly low quality. SFT improves both refusal fluency and precision and benefits substantially from the larger, noisier silver-tier data, while DPO sharpens refusal precision but comes at a steep, largely data-invariant cost to linguistic quality. No single configuration jointly maximizes safety, helpfulness, and fluency. Our results suggest that current alignment techniques teach models when to refuse more readily than how to do so fluently in underrepresented languages, and that refusal-rate metrics alone are an unreliable signal of safety in low-resource settings.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37244

Preserving Separation Logic Specifications through Compilation

Carmine Abate, Kleio Liotati, František Farka, Sebastian Ertel

原文摘要

Program specifications in separation logic describe ownership of resources and serve as logical interfaces for local reasoning. Compiler correctness, expressed as semantics preservation, does not by itself supply such an interface for compiled code, because it does not explicitly relate source and target resources and assertions. We investigate WP-preserving compilation: when a compiler translates a source program, the weakest preconditions that the program satisfies in a separation logic carry over to the compiled program. Our proof technique consists of a resource-aware simulation over interaction trees: it relates the resources required by corresponding source and target events, and tracks ownership through target operations, such as register accesses, that have no source counterpart. We apply the approach to a compiler from a structured imperative language to an assembly-like language, first for closed programs and then extended with modules and function calls. In the extended setting, each module can be verified in the source logic and compiled separately; its specifications carry over to the compiled module and are preserved when compiled modules are linked. All results are mechanized in Rocq.

cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37243

TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment

Erwei Hou, Yue Hu

原文摘要

Traditional Chinese Medicine (TCM) syndrome differentiation is usually evaluated as static final-label selection over complete clinical records. This setting hides three diagnostic behaviors: whether a model distinguishes semantic-neighbor syndrome labels from easy random distractors, whether it updates predictions as evidence fields are revealed, and whether it should commit under uncertainty. We introduce TCM-DiagCommit, a benchmark derived from the public TCM-SD/ZY-BERT resource while retaining its source syndrome labels; it converts 1,834 source cases into 23,842 task rows over 148 syndrome labels. The benchmark combines random, profile-neighbor, and full-vocabulary candidate ladders with staged t1/t2/t3 evidence. It also includes fixed-label tongue/pulse perturbations and insufficient-evidence variants. A benchmark-defined action contract scores commit, acquire, defer, and abstain. Across five zero-shot DirectLLM calibrations, random10 top-1 accuracy is 63.2% to 66.4%, but hard20 falls to 24.7% to 30.3% and full148 to 14.8% to 22.3%; on hard20, WT(all) wrong-terminal commits remain 62.2% to 74.3%. These results show that final-answer accuracy alone is insufficient for diagnostic benchmark evaluation: answer selection, evidence use, and benchmark commitment scoring should be measured separately.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37242

Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation

Saiful Khan, Afrah Farea

原文摘要

Large language model (LLM) agents that call enterprise APIs must select the correct endpoints, follow process order, use valid payload keys, and choose coded values from predefined lists. However, current retrieval-augmented service discovery treats endpoints independently and therefore misses process and schema constraints. We address this limitation by integrating Open Data Protocol (OData) metadata and Business Process Model and Notation (BPMN) reference processes in a typed property graph. A hybrid retriever identifies candidate endpoints using dense embeddings and follows process edges to retrieve subsequent endpoints. We evaluate the method on 42 enterprise services with process-chain ground truth. For queries with low lexical overlap between the query and downstream entities, it improves Recall@3 by 5.7 points (n=74), with consistent gains across embedding models and cut-offs. It matches dense retrieval on other queries and provides no improvement on OpenAPI services without a process layer, indicating that the gains arise from process structure. We also evaluate an LLM agent on 81 multi-step queries. It completes 38.7% of tasks, compared with 10.3% for a chunk-based baseline. In an elicitation probe, providing valid code lists eliminates invented codes but leaves invalid keys in 46% of write runs. Full typed context reduces invalid calls to 3% (3 of 101 runs), with no invented codes. These results show that exposing process and schema constraints during retrieval improves the reliability of agent-driven API calls.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37239

When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning

Vincess Dongmo, Astride Melvin Fokam Ninyim

原文摘要

Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a different price to manipulate each relation and each action; taking such costs as given, we ask when using a relation is worse than ignoring it. Our first main result proves that degree gating strictly beats every selection or reweighting of a relation when part of the population is isolated on it and the attacker cannot afford to open the gate, and that this window is sharp; on real graphs, validated gating gains exactly on the relations that meet these conditions and nowhere else. Our second shows that a per-node exposure bound, which extends to message passing, tells a platform which relation to harden: exposure per unit cost, computed without any attack, picks the relation whose hardening raises the exact trap threshold most in 15 of 16 cases, against at most 7 for informativeness, cheapness, or an analysis with equal edit costs. Supporting tools give exact worst cases for linear relational models, certified brackets for R-GCN and tree ensembles, and a finite-sample guarantee for adversarial validation, under which clean-trained graph detectors fall below their graph-free counterparts in 58 of 90 settings on six graphs. A selection protocol built on these results is never significantly worse than ignoring the graph; with at most four relations it mostly abstains, as validation alone would, and its cost-aware proposals help when relations are many, so far shown on synthetic graphs. Without cost information, the safe choice is to abstain.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37238

Peers4U: Designing Learner-Centered Virtual Peers for Children's Multimodal Mathematics Learning

Zhi Zheng, Binglin Liu, Weihao Chen, Lan Luo, Yu Mei, Jie Cai, Chun Yu, Yuanchun Shi

原文摘要

In early mathematics, children learn abstract concepts through concrete representations, such as manipulating objects, drawing, and speaking. Learning with peers can enrich this process by exposing children to diverse strategies and enabling them to exchange ideas through interaction. We realized this potential with virtual peers in Peers4U, a multimodal learning system to enhance children's mathematical conceptual understanding. Virtual peers driven by LLMs are personalized to the learner's cognitive level and assigned multimodal solutions with inspectable processes. During learning, peers engage in mixed-initiative interactions by responding, initiating topics, and advancing discussions along a pedagogical progression. A user study with 22 children and two experts showed our learner-centered topic orchestration significantly outperformed a persona-centered baseline, and children spontaneously authored new artifacts to demonstrate inspired ideas or share their own strategies, producing significantly more solutions when grouped with more Leading Peers. We contribute design insights for multimodal, learner-centered virtual peer systems.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37237

GraphRAGProv: GraphRAG Meets How-Provenance

Wadie El Amrani, Luis Galárraga

原文摘要

GraphRAG systems often use knowledge graphs to retrieve relevant context for an LLM that produces the final answer. That makes answers more inscrutable and therefore less appealing for domains where transparency is paramount. We present GraphRAGProv, an architecture that executes SPARQL queries over source-grounded RDF graphs to compute answers and their how-provenance polynomials. These polynomials record which statement occurrences were used and how they were combined. Because each occurrence is linked to its source text, users can follow these links to check whether the extracted statements reflect the text and whether the query combines them to answer the question. Querying thereby becomes a way to inspect and evaluate the text-to-graph transformation. Our interactive demo examines 400 cases from two multi-hop QA benchmarks, revealing extraction and query errors even when the final answer is correct.

cs.AI · cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.09346

Evaluating Geographic Lexical Knowledge in Large Language Models Across 21 Spanish-Speaking Countries

Yoshifumi Kawasaki

原文摘要

Large language models (LLMs) increasingly serve users across regional varieties, yet their knowledge of geographic lexical variation remains insufficiently evaluated. We investigate country-conditioned lexical usage judgments in Spanish using an expert-curated database covering 934 lexical items across 21 Spanish-speaking countries. Treating ten proprietary and open-weight LLMs as virtual informants, we evaluate two complementary question formats: Yes-No question format (YNQF) and multiple-choice question format (MCQF). The evaluation comprises 10,164 YNQF questions and 16,637 MCQF questions, assessed using F1 and an adjusted Jaccard coefficient, respectively. Results reveal substantial differences across models, countries, and formats. Spain receives the highest country-level score for eight models in YNQF and nine in MCQF; Chile receives the lowest MCQF score for every model. Regression analyses suggest that digital resource volume is generally more strongly associated with YNQF performance, whereas lexical distance from Spain is more strongly associated with MCQF performance. These findings provide a fine-grained diagnostic of uneven regional lexical knowledge and highlight the importance of complementary elicitation formats and evaluation metrics. The benchmark measures explicit usage judgments, motivating separate assessment of region-appropriate generation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37236

HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision

Yongqi Shan, Yunzhi Zhuge, Huchuan Lu

原文摘要

Semi-supervised semantic segmentation, which aims to utilize large volumes of unlabeled images to achieve accurate segmentation results with fewer human annotations, has attracted increasing attention. Prior methods were primarily based on the assumption that the pseudo-labels generated by each branch were sufficiently reliable to supervise the remaining branches. However, there is a concern that the errors in pseudo-labels could accumulate during co-training, potentially resulting in suboptimal performance. To this end, we present a novel framework called heterogeneous dual-branch voting supervision (HDVS), which is designed to enhance the reliability of pseudo-labels and mitigate the issues arising from pseudo-labeling. Specifically, based on the cross-supervision framework, we introduce a voting mechanism that correlates pseudo-labels from heterogeneous branches to produce pseudo-labels with enhanced reliability. Concurrently, we employ a feature communication module to introduce perturbations at the feature level in each branch to maximize prediction diversity across the dual branches while maintaining convergence. Comprehensive evaluations of the proposed HDVS on two benchmark datasets (PASCAL VOC 2012 and Cityscapes) demonstrate its superiority to the state-of-the-art approaches.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37234

Asynchronous Verifiable and Complete Secret Sharing: From Design Patterns to System-Level Trade-offs

Joachim Bruneau-Queyreix, Martin Zivojinovic, Leo Mendiboure, Tom Claudel, Laurent Réveillère

原文摘要

Modern secret sharing protocols promise robust secret sharing in fully asynchronous Byzantine systems, but their practical costs remain difficult to compare across papers, assumptions, and workloads. The difficulty is not merely experimental: protocols with similar asymptotic guarantees often place very different work on the critical path through their choices of dissemination, verification, batching, and recovery. This paper turns that fragmented research landscape into a corpus-backed designspace analysis and systems evaluation of asynchronous verifiable and complete secret sharing. We derive a design sieve, select seven representative protocols, and implement them in a common Rust framework. In our experiments on the Grid'5000 platform, we evaluate honest-dealer and faulty-dealer stress executions using latency, throughput, message count, bandwidth, and aggregate CPU-time. The results show that message complexity alone poorly predicts latency, that optimistic paths can be dominated by recovery cost, and that batching or packing helps only when verification stays off the critical path. These findings turn protocol-by-protocol comparisons into design-to-cost guidance for choosing, implementing, and extending asynchronous verifiable and complete sharing protocols.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.09910

Structure and Regularization of Fused Objectives in Kernel Discriminant Analysis for Small-Sample-Size Problems

Lingxiao Qu, Yan Pei

原文摘要

When the number of training samples is smaller than the dimension, discriminant analysis faces a singular within-class scatter matrix, and fused objectives that combine the total variance C, the between-class scatter S_b and the within-class scatter S_w are one way to handle it. Using the seven variants of Kernelized Linear Principal Component Discriminant Analysis (KLPCDA) as a platform, we derive the structure of such objectives in this small-sample-size (SSS) setting. The training projections split into a class-mean part and a within-class part, the two scatter operators satisfy WB = 0, and all between-class information lies in the null space of S_w. A single fusion coefficient therefore cannot change the solution, and the variants, KPCA, the regularized kernel Fisher discriminant and the null space methods lie on the boundary of one family with two parameters, the fusion ratio t and a ridge parameter mu. On six tasks from five application domains, the regularized members were more accurate than the best of the seven variants chosen on validation data on all six tasks, by 0.8 to 5.7 points, also under added noise, whereas the fusion ratio gave no gain, including in controlled experiments on dimension ratio, class imbalance and class separation. Selecting a variant per task could gain less than one point, while a fixed choice made on other tasks transferred to every held-out task. The analysis thus gives a principled default for SSS kernel discriminant analysis, with diagnostic quantities, the null space dimension and the class-size spectrum, that can be computed before training.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37231

TaskBridge: Technical Report for SIGIR 2026 eCommerce Challenge

Zhiheng Fu, Yupeng Hu, Zixu Li, Zhiwei Chen, Qinlei Huang, Shaokun Wang, Han Liu, Fan Liu 等 10 位作者

原文摘要

The SIGIR 2026 eCommerce Challenge Query Reformulation Task evaluates the reformulation of task-oriented queries into expressions suitable for product retrieval, followed by BM25-based retrieval. These queries often imply product needs through activity-level semantics, creating a lexical gap with catalog descriptions. Systems must preserve task intent while adapting the number of reformulations to the Automatic and Interactive protocols. We propose TaskBridge, a catalog-anchored framework comprising Catalog Semantic Anchoring, Unified Five-Candidate Rewriting, and Protocol-Aware Selection. It grounds queries in catalog vocabulary, generates five complementary reformulations, and selects one query for Automatic retrieval or up to four for Interactive retrieval using BM25 scores, query-product reranking, and weighted Jaccard overlap. The selected queries are independently executed using BM25 to produce results in the required six-column format. Experiments demonstrate improved retrieval effectiveness, with multiple complementary queries providing additional gains in the Interactive setting. TaskBridge achieved first place in the SIGIR 2026 eCommerce Challenge.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37230HF 社区推荐

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Shuhuai Li, Shengdong Ye, Dongdong Ge, Yinyu Ye, Jianghao Lin

原文摘要

Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness in service evaluation, wasting limited resources, and (2) use heuristic strategies to decide admission and placement on GPUs, resulting in suboptimal scheduling decisions. To bridge this gap, we present TAO, a tool-aware joint scheduling framework for LLM-based agentic serving. Its value interface combines near-term tool readiness, node-specific cache credit with time-aware decay, and token footprint; a dynamic program jointly selects and places waiting sessions under capacity constraints. Across the 12 reported model-workload-concurrency settings, TAO reduces latency by up to 26.8%, reduces mean time to first token (TTFT) by up to 36.3%, and increases decode throughput by up to 29.5% relative to the best evaluated state-of-the-art baseline for each metric.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37229

Decision Models as Judges for Hallucination Detection

Haozheng Liu, Zhaoqian Xue, Zhongyin Wang, Junting Mu, Zihui Ma, Shuya Feng, Lingyao Li

原文摘要

Large language models are widely used as judges of model outputs (LLM-as-a-Judge), but they are costly and can hallucinate or be overconfident. Decision models are a potential alternative. They return a predefined verdict with a probability for each label instead of free-form text and are much cheaper and faster. We test this promise on hallucination detection. We build binary benchmarks for five hallucination types (9,852 items from six datasets) and compare five decision models with the generative judge gpt-6-sol. Performance depends strongly on the type: the best decision model matches gpt-6-sol in balanced accuracy on context inconsistency and comes within 3 percentage points on factual errors, but trails it by 4-8 points on logical and instruction inconsistency. Decision-model probabilities are overconfident, though less so than the GPT-6 models, and separate correct from incorrect decisions only moderately. We also find that a confidence cascade of decision models improves on the best single model by 1.9-3.3 points on three types and matches or exceeds gpt-6-sol at 1-3% of its cost. Overall, decision models are a practical low-cost judge for some hallucination types but need to be validated before use.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37228

AutoRSE: Evaluating LLM Agents as Recommendation Engineers for Self-Evolving Recommender Systems

Rui Tian, Yi Fang, Yejin Hua, Du Wang, Yuzhe Wang, Minxuan Shan, Zirui Ren, Xinyu Lin 等 11 位作者

原文摘要

Recommender Systems Engineer Agents (RSE-Agents), which use LLM-based agents to autonomously improve recommendation algorithms, are emerging as a promising paradigm. However, their capabilities and limitations remain poorly understood due to the lack of a unified, standardized evaluation framework and systematic trajectory-level analysis. To address this gap, we introduce AutoRSE, an evaluation framework spanning six representative industrial-grade recommendation tasks, and conduct a large-scale empirical study of three frontier LLMs across three widely used agent harnesses. Our results show that RSE-Agents consistently enhance the performance of backbones on five of the six tasks, with an average relative improvement of 16.1%, indicating that they can already autonomously improve recommendation performance. However, trajectory-level analysis also reveals that current RSE-Agents function primarily as engineering optimizers rather than algorithmic improvers: their gains are largely driven by hyperparameter tuning, training strategies, and model ensembling, while genuine algorithmic innovations are rare. Since the largest gains in recommender systems often stem from algorithmic advances, this behavior underscores a fundamental limitation of current RSE-Agents. To probe this limitation, we perform idea-injection experiments and show that agents equipped with innovative ideas from frontier research or human experts achieve substantially larger improvements than those relying on self-generated ideas. These results suggest that idea generation is a central bottleneck of current RSE-Agents, highlights a key direction for the future recommendation system research. Our implementation is publicly available on GitHub: https://github.com/Ray-Tiann/AutoRSE.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37227

Doubly Robust Deep Kernel Tests for Structured Outcomes

Robin Leman, Bariscan Bozkurt, Sofiane Tanji, Arthur Gretton, Houssam Zenati

原文摘要

We propose a test of whether two interventions induce the same outcome distribution when outcomes are structured and high-dimensional, such as images, text and graphs. We represent the interventional distributions as mean embeddings on learned deep features, such that the treatment effect is a doubly robust representation of the difference in mean embeddings. Our test, DR-KTE-Deep, optimises the learned features so as to maximise an estimated power criterion on this treatment effect representation. To motivate our learning objective, we show that the power criterion characterises the asymptotic signal-to-noise ratio of the test under fixed alternatives, and we derive a uniform finite-sample bound for its regularised estimate. We show that, with the learned kernel fixed, a held-out test is asymptotically valid under the null given suitable nuisance-estimation rates. Empirically, DR-KTE-Deep achieves substantially higher power than fixed and bandwidth-optimised kernel baselines across image, text and graph outcomes, while maintaining well-calibrated Type-I error.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37226

Subspace Clifford Networks

Zhongping Ji

原文摘要

In this work, we propose Subspace Clifford Networks, a reformulation that replaces global cyclic rolling with grouped subspace interactions. Instead of sampling sparse cyclic diagonals across the entire $D$-dimensional channel space, we project the features into an aligned space $\R^{\tilde{D}} = \bigoplus_{g=1}^{G} V_g$ partitioned into $G$ low-dimensional groups $V_g \cong \R^k$ with $k \in \{2, 3, 4\}$. Within each $k$-dimensional group, we compute all $\binom{k}{2}$ wedge coordinates and concatenate them with $\operatorname{SiLU}$-activated coordinate-wise products, while sandwiching the grouped interaction between learnable $1\times 1$ linear projections to enable cross-group channel mixing. This design reduces intermediate feature expansion from $2|\mathcal{S}|D$ (typically $10D$ for 5 shifts) down to $1.5\tilde{D}$ ($k=2$), $2.0\tilde{D}$ ($k=3$), or $2.5\tilde{D}$ ($k=4$). Furthermore, exploiting the small, fixed group size $k \in \{2, 3, 4\}$, we implement a fused CUDA kernel that evaluates the forward interaction and a recomputation-based analytical backward pass using thread-local variables without allocating global-memory buffers for elementwise intermediates. Finally, we extend the backbone from an isotropic columnar layout to a multi-resolution Hierarchical Clifford Network with configurable per-stage subspace dimensions. Experiments on CIFAR-100 show that the proposed models substantially reduce parameter count and training time across both regimes, while the hierarchical variants also improve classification accuracy over the evaluated shift-based hierarchical baselines.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19769

When Does the Dependency Graph Help Code-to-Architecture Mapping?

Rakhshanda Jabeen, Morgan Ericsson, Jonas Nordqvist, Anna Wingkvist

原文摘要

Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source files and architectural modu les is missing, incomplete, or costly to maintain manually. We formulate code-to-archite cture mapping as semi-supervised node classification over a directed multi-relational de pendency graph, with files as nodes, typed dependencies as edges, and lexical features d erived from code identifiers and directory layout. Starting from a small labeled sample, an iterative self-training procedure expands the mapping to the remaining files. We com pare a graph convolutional network (GCN), a graph attention network (GAT), and a graph-f ree multi-layer perceptron (MLP), using identical features and training procedures for t he learned models, against a Naive Bayes reference. Across 100 runs on ten open-source J ava and C/C++ systems, all three neural models outperform the reference on both F1 metri cs. GAT achieves the highest averages of system-level median macro and micro F1, at 83.5 and 92.2, respectively, whereas MLP remains competitive or superior on several systems. On Chrome, the largest system with 18,343 files, GAT and GCN exceed MLP by 22 and 19 ma cro-F1 points, respectively, and have substantially fewer persistently misclassified fil es. Connectivity and homophily are associated with where neural message passing helps, w hile multi-relational aggregation outperforms a single merged edge type on every system for both GCN and GAT. A follow-up study finds that several model rankings depend on the training seed, qualifying smaller advantages without removing the large graph benefit ob served on Chrome.

cs.SE · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37225

Sharpness-Aware Muon: Matrix-Aware Optimization with Momentum-Guided Perturbations

Zhiwei Zhai, Wenjing Yan, Ying-Jun Angela Zhang

原文摘要

Muon is a matrix-aware optimizer that combines momentum with orthogonalization to produce structured update directions with strong empirical behavior. However, it only shapes the geometry of the update itself and does not explicitly control neighborhood worst-case loss or bias training toward flat regions, which are often linked to stronger generalization. To address this limitation, we introduce the sharpness-aware formulation of Muon. We first develop \textsc{MuSAM}, which incorporates Sharpness-Aware Minimization (SAM)-style perturbation into Muon's orthogonalized update and establishes a principled bridge between sharpness-aware training and matrix-aware optimization. We then show that this formulation faces an efficiency--stability tension: constructing the perturbation requires an extra gradient evaluation, while the perturbation itself is generated from a single minibatch gradient and is therefore noisy. To resolve this issue, we propose \textsc{MoMuSAM}, which turns Muon's momentum from an update variable into a sharpness-probing signal. By using normalized momentum as the perturbation direction, \textsc{MoMuSAM} removes the extra clean-gradient computation and replaces the single-batch perturbation proxy with a temporally aggregated one. We prove that both \textsc{MuSAM} and \textsc{MoMuSAM} attain the same asymptotic first-order stationarity order, and further show that \textsc{MoMuSAM} yields a more stable stochastic linearization than \textsc{MuSAM}. Experiments on standard benchmarks demonstrate that sharpness awareness consistently improves Muon.

cs.LG

查看论文
arXiv ↗PDF ↗