QA
-
ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer
2026-10-15 06:10:24Hao Shi, Jiafeng Wang, Yuzhuo Fu, Tao Zhang, Jian Bai, Juelu Zhang, Qing Cui, Chao HuangAbstract
Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass outputs still miss small objects, text, and spatial relations or promote uncertain observations into confident claims. We formulate fine-grained captioning as recoverable visual information transfer, in which a teacher acquires missing evidence under a finite observation budget and converts it into reusable supervision. ZoomCap uses a draft caption to route conditional knowledge retrieval, OCR-sensitive reading, coverage-gap recovery, and adaptive visual zooming, allocating deeper crops only to the most complex eligible region, deriving spatial relations from grounded geometry, and fusing non-duplicate evidence. We also introduce FactCycle, which scores caption-derived atomic claims on two blind anchors--source image (truthfulness) and reconstruction (realizability)--separating fabrication from generator loss claim by claim; human and multi-judge comparisons complement this fact-level view. Against Qwen3.5-397B-A17B captions, ZoomCap achieves an 81.9% human tie-adjusted preference score with a teacher over 10x smaller, and FactCycle counts 52.4 transferred claims per image vs. 31.5 for ScaleCap. The evidence also transfers: in continual pre-training, ZoomCap-450K improves the 11-benchmark average by 1.31-2.38 points over the strongest competing corpus and Ling-Tiny-VL-v3 gains 1.4 points on a production document/OCR monitor suite (1.5 on perception) at 60B tokens; in medical pre-training, 2.64M ZoomCap-captioned images improve five VQA benchmarks by 3.04 points (vs. 1.76 for same-image Gemini-3.1-Pro captions).
Abstract (translated)
URL
https://arxiv.org/abs/2610.21320
PDF
-
Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG
2026-10-15 06:08:04Eunchan Jo, Seounghyun Jang, Sangwoo MoAbstract
Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model reads the retrieved pages. We find that evidence in retrieved pages remains underused even when the correct pages are retrieved. On SciEGQA oracle pages, five prior methods give the generator 0.7K to 2.7K visual tokens per query on average under a common image processor, yet raising the page-only budget from 1K to 32K improves accuracy by 15.22 points. At a fixed 16K budget, adding ground-truth crops improves accuracy by 3.75 points over page-only input. We study what the generator needs from retrieved pages through two requirements: Loud, making full use of visual token capacity, and Clear, refining the page so that its evidence becomes prominent. For Loud, increasing either the visual token budget or visual fidelity, the image resolution those tokens preserve, improves accuracy with the other held fixed, and full-page scaling outperforms repetition and tiling at matched budgets. For Clear, suppressing surrounding content improves accuracy without enlarging selected regions, and adding OCR of these regions to page images outperforms either input alone. We implement both as Loud and Clear (LoC), which combines higher-resolution pages with OCR from query-relevant regions without ground-truth annotations or additional training. LoC outperforms eight prior methods on SciEGQA, ViDoRe-v3, and MMLongBench-Doc, improving over the strongest, ColQwen3, by 8.88, 3.09, and 4.22 points with the same retriever and generator. It also outperforms its page-only variant under the same visual token budget. These results locate a bottleneck beyond retrieval: how the retrieved pages are given to the generator.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21318
PDF
-
PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning
2026-10-15 05:56:53Max Rosenblattl, Nikhil Krishnaswamy, Leon Nissen, Manuel Milling, Nicolas Zumarraga, Ning Wang, Thomas Kaar, Robert Jakob, Bj\"orn W. Schuller, Elgar Fleisch, Patrick Langer, Paul SchmiedmayerAbstract
Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence. This representation is poorly matched to personal health systems that need to retrieve, route, or summarize sensor evidence while preserving temporal structure. Cloud-hosted time-series language models avoid smartphone limits, but they repeatedly move sensitive physiology off the device and add latency and per-query compute cost. Mobile model alternatives that aggregate time-series data into statistical features or serialize raw samples as text either compress temporal structure or exhaust the context and memory budgets of small on-device models. We present PocketTSLM, a mobile-native deployment of OpenTSLM SoftPrompt, the soft-prompt variant of the OpenTSLM time-series language model. PocketTSLM runs fully on a consumer smartphone by injecting encoded time-series windows as embeddings instead of tokenizing time series as text. A numerical parity protocol verifies identical greedy-decoded token sequences between the Swift port and a Python reference using Apple's MLX machine-learning framework. Answers also match the PyTorch reference, although rationale wording can differ. An on-device context-economics benchmark compares the soft-prompt path with a text-serialized baseline on the same backbone. In our benchmark format, soft-prompting uses approximately 12 times fewer time-series tokens and reduces prompt-prefill cost. PocketTSLM processes 30-second Sleep-EDF electroencephalography clips for sleep staging and a 1,000-sample (10 s) 12-lead electrocardiogram clip from ECG-QA. In comparison, text-serialized baselines exceed the phone's context or memory budget at longer time-series windows. All inference runs entirely on the device, with no health data transmitted during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21308
PDF
-
TRACER: A Multimodal Harness for Patient Care in Hospitals
2026-10-15 05:00:47Zane Durante, Paul Tang, Keshigeyan Chandrasegaran, Amit Kaushal, Shrinidhi Kowshika Lakshmikanth, Feolu Kolawole, Yu Jun Zheng, Yifan Geng, Shobhit Agarwal, Kevin Schulman, Juan Carlos Niebles, Ehsan Adeli, Arnold Milstein, Li Fei-FeiAbstract
Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central challenge is how to represent behavior across the entire stay while preserving access to fine-grained visual and clinical evidence. We introduce TRACER, a training-free multimodal harness that constructs minute-level action records from video and combines them with clinical records into hourly reports. The harness equips an LLM agent with tools to query this hierarchy, inspect relevant video, and retrieve clinical records. To evaluate TRACER, we construct two benchmarks. The first contains 397 annotated one-minute clips spanning 15 atomic actions; the second poses 144 clinician-informed multiple-choice questions, grounded in 264 hours of video and clinical records from two ICU patients. TRACER achieves up to 84.8% accuracy for action detection and 61.0% QA accuracy versus 49.3% for the strongest baseline using the same backbone. Across 280 patients spanning approximately 60,000 camera-hours, TRACER identifies significantly less purposeful activity in patients with a positive delirium assessment during their stay than in those without (p < 0.0001). Our results show that combining continuous video with clinical records can support understanding of patient behavior over time and across patient cohorts without training on protected health data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21266
PDF
-
What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?
2026-10-15 04:47:09Subigya Nepal, Ruth Heo, Emma M Parrish, Colin A DeppAbstract
Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements urging users who disclose suicide thoughts to seek help from crisis lines or other human sources. How chatbots respond when users refuse that help is unclear. This cross-sectional audit ran 2,550 scripted multi-turn conversations in September 2026. Each conversation opened with a disclosure of suicide thoughts at 3 levels of severity, answered every referral with up to 10 standardized refusals and then changed the subject. All 2,550 conversations included a referral, 2,542 (99.7%) in the first reply. However, mean persistence ranged from 0.01 to 9.94 refusals across chatbots. Newer versions of all 5 chatbots tested in 2 versions persisted less than older versions (each P < .05). Compared with passive ideation, a disclosure of intent was associated with 1.26 more refusals sustained (95% CI, 1.06-1.46) and higher odds of renewed referral after the topic change (odds ratio, 10.07; 95% CI, 7.43-13.66). Chatbots that persisted less in referral more often presented themselves as the user's support (Spearman rho = -0.80; P < .001). Of 8,818 refusal-phase replies urging outside help, only 173 (2.0%) asked about barriers to seeking it. Chatbots uniformly recommended outside help after disclosures of suicide thoughts but varied widely in persisting in those recommendations, with newer versions persisting less. Safety evaluations should test what happens after a crisis referral is refused, not only whether one is offered.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21253
PDF
-
Judging the Judges: Confidence and Disagreement in Rubrics as Rewards
2026-10-15 03:35:00Michael Tian-Yue Liu, Anne Harrington, Trevor Darrell, Yutong BaiAbstract
Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric. Prior work has focused on improving the rubric or strengthening the single judge, with comparatively little attention to how different single or multiple judges might be used during RaR training. We first show that judge identity alone produces a substantial spread in scores when training Qwen3-4B-Base on RaR-Medicine and RaR-Science across five frontier and open-weight judges. Building on this, we propose RaRE (Rubrics as Rewards with Ensembles), a novel judge ensemble strategy for RaR with two mechanisms: a soft-Likert reward that uses judge logprobs to weight more confident judges more heavily, and a drop-on-disagreement mask that excludes high-disagreement rollouts from the GRPO update. We find that this design is critical: while a naive average of judge scores fails to outperform the best single judge, RaRE outperforms every single-judge RaR variant on both HealthBench and GPQA Diamond, with per-theme analysis showing that it inherits the complementary strengths of its constituent judges. Our findings establish judge ensembling as a compelling axis for improving RaR.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21179
PDF
-
When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation
Abstract
Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consistency can serve as a proxy for correctness when ground-truth labels are unavailable or expensive to obtain. In this paper, we test this assumption directly. Using four financial QA datasets (multiple-choice and free-form), ten consistency dimensions, and two frontier model families, we measure the joint distribution of consistency and accuracy at the level of individual examples rather than in aggregate. We find that 60% of all incorrect answers fall in the high-consistency region (consistency $\geq$ 0.8), and that 77.7% of these show complete answer collapse, i.e. identical wrong answers across all perturbation variants. This high-consistency/incorrect quadrant cannot be detected by any evaluation signal that is built on agreement alone, as the model appears maximally reliable while being wrong. We show that the phenomenon is robust to the choice of consistency threshold t (it persists from t=0.50 to t=1.00), is shared across model families, and is concentrated in specific intersections of perturbation dimension and domain. We map where this quadrant occurs, analyze its stability properties, and discuss the implications for evaluation pipelines that use agreement-based signals in place of human labels.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21128
PDF
-
SHIP: Structured and Hierarchical Insight with Privacy
2026-10-15 00:48:25Kai Chen, Guisi Ni, Albert Cheu, Kassem Fawaz, Yuzheng Hu, Ryan McKenna, Peter KairouzAbstract
Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce private insights in diverse forms for different analytical purposes, making their utility difficult to assess and compare. In this work, we formulate differentially private (DP) insights as reusable representations for answering analytical queries, providing a common basis for utility assessment. Answering these queries, however, requires fine-grained details and cross-attribute statistics that existing representations may omit. To capture this information, we introduce Structured and Hierarchical Insight with Privacy (SHIP), which automatically maps queries to attributes, builds a hierarchical hybrid taxonomy, and releases a DP synthetic table for further analysis. We also develop an evaluation protocol based primarily on QA performance and structured fidelity. Our experiments demonstrate SHIP's strong performance on both measures relative to existing private insight baselines, while identifying queries that remain challenging for structured representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21048
PDF
-
Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models
2026-10-14 22:04:32Frank F. Yang, Kefei Yan, Yiren Wang, Yiyang WangAbstract
Improving the reasoning capabilities of vision-language models (VLMs) often relies on post-training with supervision from stronger models. Two common strategies are supervised fine-tuning (SFT), which trains on teacher-generated demonstrations, and on-policy distillation (OPD), which provides teacher feedback on trajectories generated by the student itself. While OPD can be more data-efficient by supervising student-generated trajectories, it is unclear how the teacher's supervision at each state affects the student's learned behavior. To study this question, we conduct a controlled comparison of OPD and filtered SFT across data budgets and tasks where the teacher exhibits different levels of reliability, and analyze how these differences shape student accuracy and completion behavior. Across the two tasks, we find that OPD is effective only when the teacher remains reliable on student-generated trajectories. On ChartQA, where the teacher completes 99% of its solutions, OPD trained on only 10% of the data comes within 1.4 accuracy points of full-data SFT. In contrast, on Geometry3K, where the teacher fails to complete 22% of its solutions, OPD underperforms SFT by 7.9 points, with most of the gap explained by incomplete responses. More strikingly, starting OPD from an SFT student reduces its completion rate from 76% to 62%, effectively erasing the completion behavior learned through SFT. Filtering teacher demonstrations for completeness alone recovers much of SFT's advantage. These results show that on-policy supervision can transfer not only teacher knowledge but also persistent failure modes on student-visited states. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20989
PDF
-
VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
2026-10-14 21:36:28Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yazhe Hu, Lan Guo, Yuying Wang, Mengqing Guo, Bhavesh Dnyaneshwar Gore, Shubham Pathak, Ramapriya Ranganath, Sandeep Sharma, Tao Sheng, Sujith Ravi, Dan RothAbstract
Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation failures. We present VELD-QA, a large-scale benchmark for Visual Evidence grounding and question answering in Long Documents. It contains 15,000 fully human-authored question-answer pairs across 5,859 real-world PDFs totaling 372,445 pages, balancing chart, table, and complex-layout tasks. Human annotations identify supporting pages and evidence elements and describe cited visual content, enabling separate retrieval and interpretation evaluation. We evaluate nine vision-language models under four evidence settings and seven retrieval-augmented and agentic systems. Our analysis identifies bottlenecks in evidence localization and interpretation. Retrieval-based methods substantially underperform the oracle setting with ground-truth supporting pages; full-document access does not close the gap. Localization alone is insufficient: oracle accuracy peaks at 81.7%, highlighting persistent visual interpretation and reasoning challenges. Enriching inputs with our visual-element annotations narrows the performance gap by 17-24%, demonstrating value beyond evaluation and motivating data enrichment for multimodal document QA. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20964
PDF
-
When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following
Abstract
A reasoning trace retained at answer time plays two roles: it can raise accuracy, and it can compete with the current evidence when the two disagree. We disentangle these roles by crossing verified evidence versions with the traces generated from each and answering from the same traces and evidence under two configurations: continuation of the model's own thinking and a separate answer call. Across three model families (gpt-oss, Gemma4, Qwen3) on HotpotQA and MuSiQue, the separate call raises evidence-following over continuation by 29.9 to 60.6 points. On the same pairs, removing the trace lowers accuracy by similar amounts under both configurations. Yet continuation repeats the stale conclusion in most conflicts, and the separate call follows the current evidence far more often. Benefiting from a trace and deferring to it are therefore distinct properties. Further analyses show that the final line of a trace carries most of its value, gold evidence helps most before the trace is written, distractors weaken correction under a separate call, and renewed reasoning, unlike a verification instruction, follows the current evidence in most conflicts. Because trace deletion alone cannot reveal which source an answer follows, evaluations should report both properties together with the answer configuration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20805
PDF
-
Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization
2026-10-14 16:45:14Lei Xu, Xin Quan, Andr\'e FreitasAbstract
Autoformalization (AF) requires both prover acceptance and fidelity to an informal source, but prover acceptance alone cannot establish fidelity, and expert-validated reference formalizations are costly to obtain. We introduce a reference-free proxy-judge framework, which separates correctness into grounding, statement faithfulness, coverage, and inference, and a theory of how imperfect checks shape iterative refinement. We establish three results. First, for a fixed sequence of candidates, an added proxy's false-positive and false-negative rates bound its effect on the pass-but-wrong rate. Second, damage to a correct formalization requires a false rejection that exposes it to further refinement, and harmful revisions are then retained through unguarded changes, missed changes, or prover progress that overrides judge warnings. Third, a decomposition of the final pass rate distinguishes continued refinement, generation of new candidates, and their success in passing the checks. We instantiate the framework with eight proxies and test these predictions on ProofNet and miniF2F in Lean~4 and on e-SNLI and ProntoQA in Isabelle/HOL. Under single-proxy removal, no prediction written before the runs is contradicted, and all traced breaks follow the identified failure routes. The results connect proxy reliability to the benefits, risks, and limits of refinement without reference formalizations.
Abstract (translated)
URL
https://arxiv.org/abs/2606.09449
PDF
-
IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation
2026-10-14 16:29:11Gaolei He, Jinhui Li, Ruobing Zuo, Xia Zeng, Zhengfeng YangAbstract
Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We introduce IneqAgent, an agentic framework combining LLM reasoning with symbolic computation for inequality proving in Lean4. Lemma-level Monte Carlo Tree Search coordinates lemma construction, goal reformulation, and symbolic backend selection. Complementary sum-of-squares, Bernstein, and successive difference-substitution backends produce exact certificates for local Lean proof generation. The agent integrates these proofs with LLM-generated steps and uses Lean feedback to construct complete proofs checked against the original theorem statements. On four benchmarks, IneqAgent with DeepSeek-V4-Flash solves 175 of 186 problems (94.09%), achieving the highest overall success rate among the evaluated methods. Across four backbones, it achieves higher success rates at low LLM inference cost thresholds than Direct Agent using the same backbone, with lower mean inference costs over each method's successful runs. We also obtain Lean-verified strengthenings of Dittert's conjecture in dimensions four and five, and certify the Holens--Djokovic $(4,4)$ inequality, implying Merris's conjecture in dimension four.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20681
PDF
-
Repairing Speech Access After Text Updates with Frozen Affine Fields
2026-10-14 14:24:38Ming-Hao Hsu, Yuxiang Wang, Yingda Shen, Zhizheng WuAbstract
Speech-capable language models inherit most of their knowledge from text-rich language backbones, and continued model maintenance is likewise dominated by text updates. Knowledge acquired through a text update can nevertheless remain difficult to access when the same query is spoken. We formulate this mismatch as post-update speech access repair, where the knowledge-bearing checkpoint stays frozen and a detachable operator repairs speech-only access in one model pass. We introduce Affine Fields for Interface Repair across Modalities (AFFIRM), which first learns and freezes a base correction for speech hidden states, then adds query-specific corrections with zero mean over the operator-training queries. Paired speech and text states provide the coordinates that condition these corrections on each query. On balanced synthetic-speech PopQA, paired comparisons do not establish a clear advantage for AFFIRM over global SALSA steering or low-rank ReFT interventions under the same frozen single-state constraint. On recorded SLUE-SQA-5 questions with text passages, a full-scale PopQA-fitted AFFIRM operator transfers without refitting and improves ROUGE-L by 0.0941 over its paired No Repair baseline. Low-rank ReFT interventions also transfer positively, whereas the matched SALSA variant falls 0.0707 below its paired baseline. These results show that text acquisition and speech access can diverge after an update and should be verified and repaired separately.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20253
PDF
-
AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining
2026-10-14 12:24:40Yunhao Wang, Feng Zhang, Tinghao Yu, Xing Wu, Jiang ZhouAbstract
Synthetic data is increasingly used in language-model pretraining. Existing knowledge-corpus synthesis pipelines, including WRAP and Nemotron-CC, usually take a source passage or document segment as input and generate rewritten or QA-style samples from that text. This can improve surface form and prompt diversity, but it does not explicitly require fine-grained source facts -- especially secondary entities, list/table entries, and precise temporal attributes -- to appear in the synthesized corpus. We propose AFCS (Atomic-Fact-Conditioned Synthesis), a pipeline that first extracts source-supported atomic facts and then uses each retained fact to drive generation. AFCS uses structure-aware extraction over the document tree, source-grounded verification, local context expansion, and multi-format generation. In continued-pretraining experiments with OLMo-3-7B and a 32B base on the same FineWiki source corpus, AFCS outperforms WRAP and Nemotron-CC on SimpleQA, SimpleQA Verified, PopQA, and HotpotQA. Granularity ablations show that fact-level synthesis improves over chunk-level, paragraph-level, and entity-level synthesis; and a 100B-token mid-training integration improves factual benchmarks and raises the 12-task general benchmark average by +1.09.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20086
PDF
-
Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering
2026-10-14 12:23:59Yi Wang, Tianzi Wang, Tong Lei, Dahan Wang, Peter BellAbstract
Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understanding systems requires suitable textual interfaces through which multimodal reasoning can be exposed to text-based optimizers. We investigate how the design of textual interfaces affects prompt optimization for multimodal reasoning, on the audio-visual question answering task. We compare three interface designs, including a direct inference system consisting of a single omni-modal large language model (OmniLLM), a captioner-reasoner system, and an agentic architecture in which a primary agent orchestrates subagent OmniLLMs. Experiments with Qwen3-Omni and Gemini show that direct prompt optimization provides model-dependent gains; the captioner-reasoner system and the agentic system expose more interpretable optimization interfaces but are harder to optimize, where error analysis of cases affected by optimization is conducted. Our study highlights textual interface design as an important factor in making prompt optimization effective for omni-modal reasoning systems. Our implementation details are specified in GitHub repo.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20085
PDF
-
VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs
2026-10-14 12:20:56Chen Chen, Zheming Liang, Jiaqi WangAbstract
Visual world knowledge is a core capability of multimodal large language models (MLLMs), underpinning knowledge-intensive visual question answering and fine-grained visual reasoning. However, existing benchmarks remain limited in two key respects. First, their category coverage is narrow: most benchmarks span only a small number of categories across a few domains, falling far short of the open-ended scale of real-world visual entities. Second, their task construction is often insufficiently rigorous: models can answer correctly using coarse-grained cues, vague associations, or elimination strategies without truly mastering precise concepts, making it difficult to accurately assess their knowledge of fine-grained entities. We introduce VisualWorldBench, a taxonomy-grounded multi-task benchmark built on a hierarchical taxonomy of 21,291 leaf-node classes across 8 visual domains, with 32,541 evaluation instances whose ground-truth labels cover 15,479 categories across four complementary tasks: closed-set recognition, contrastive selection, precise localization, and open-world naming, covering different directions of knowledge retrieval and varying degrees of answer openness to comprehensively evaluate visual world knowledge. Most questions are constructed from taxonomically proximate categories, forcing precise discrimination among fine-grained entities. Experiments reveal that the strongest closed-source model achieves only 80.4% average accuracy, exposing capability gaps hidden under conventional benchmarks. We further construct VisualWorldBench-50K, a training resource covering 50K+ categories. Fine-tuning on VisualWorldBench-50K yields over 21 percentage points improvement on VisualWorldBench, with consistent transfer to public fine-grained recognition and visual knowledge benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20083
PDF
-
What Is a Clarification? Estimating Model-Dependent Input Ambiguity
2026-10-14 11:54:42Jingqin Tang, Tim Tomov, Sebastian Schmidt, Dominik Fuchsgruber, Stephan G\"unnemannAbstract
Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a property of the input, yet for a particular language model, only some alternatives may be known and answerable. We therefore distinguish world ambiguity, capturing all alternatives admitted by an input, from model ambiguity, capturing those accessible to the responding model. To characterize these alternatives, we formalize natural-language clarifications through three desiderata: \emph{uniqueness}, \emph{faithfulness}, and \emph{answer equivalence}. We show that these desiderata induce a one-to-one correspondence between valid answers and equivalence classes of clarifications, implying that any interpretation can be represented either by its answer or by the clarifications that uniquely express it. We leverage this correspondence to introduce \circleclar{}, a black-box method that estimates the set of answers available to a model by checking consistency along an answer--clarification--answer cycle. Across open-domain QA and executable Text-to-SQL, \circleclar{} achieves strong recovery of these answer sets. In QA, the recovered support yields the strongest overall performance in model-dependent ambiguity detection and enables effective selection among answering, clarifying, and abstaining. Together, these results demonstrate the practical value of a model-dependent view of ambiguity and its characterization through an answer-clarification correspondence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20052
PDF
-
Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
2026-10-14 11:27:34Junru Zhang, Jinyong Wen, Bin Dou, Wuliang Huang, Baokun Wang, Yu Cheng, Weiqiang Wang, Cheng PengAbstract
Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) prediction. However, their unidirectional constraint limits bidirectional information flow, hindering cross-modal interactions and the joint preservation of multi-source signals. Consequently, the learned static representations struggle to accommodate the distinct evidence requirements of diverse downstream scenarios. We address these limitations by unlocking the iterative denoising process of diffusion language models (dLLMs) as a multi-granularity reconstruction space. Based on this insight, we propose FINDERS (FactorIzatioN of Diffusion statEs for Routing across Scenarios), a router-equipped dLLM framework comprising four operations: denoise, factorize, route, and compress. Learnable meta-slots organize complementary denoising states into transferable cross-modal semantics and modality-specific behavioral factors. To provide grounded supervision, we construct BehaviorQA, a large-scale corpus containing explicit behavioral rationales. Guided by scenario queries, a lightweight router dynamically emphasizes relevant slot directions via an input-level residual pathway before cross-source fusion and final compression. Extensive experiments and online A/B tests across ten industrial scenarios demonstrate that FINDERS consistently outperforms state-of-the-art methods in both unified and scenario-adaptive settings. This work effectively pushes the boundaries of dLLMs beyond language generation, demonstrating their immense potential as powerful user representation learners.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22400
PDF
-
Gray-Box Hallucination Detection in LLMs with Token Identities
2026-10-14 11:12:12Shaked Goldshtein, Yitzchak Grunbaum, Fabrizio Frasca, Guy Bar-Shalom, Haggai MaronAbstract
Large language models often produce fluent but factually incorrect output. Gray-box detectors identify such hallucinations from the token-probability statistics emitted during generation, avoiding the need for white-box access to hidden states that frontier models do not provide. These detectors, however, typically rely only on probability-derived representations and ignore the identities of the candidate tokens. They can therefore observe how uncertain the model is, but not what it is uncertain about. Consequently, they cannot distinguish between a model that is torn between "big" and "small" and one that is torn between "big" and "huge" when the two pairs receive the same probability distribution. We introduce GURI (Gray-box Uncertainty Representations with Identity), a lightweight gray-box hallucination detector that combines candidate-token probabilities with per-token vector identifiers. This exposes which alternatives the model considered while preserving the accessibility and transferability of the gray-box setting. Across three open-weight models and three question-answering benchmarks, GURI increases mean test ROC-AUC from 72.09% to 79.09% over a probability-only baseline. On the closed-source GPT-4.1 model, mean ROC-AUC increases from 67.39% to 71.84%. Among the three open-weight models, GURI outperforms transferred probability-only baseline in 17 of 18 directed cross-model transfers without fine-tuning. For the three open-weight models, cross-dataset transfer between HotpotQA and TriviaQA with the model held fixed improves mean ROC-AUC over transferred LOS-Net by 3.76 points.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19996
PDF
