LLM
-
TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant
2026-11-10 14:07:50Rongpei Hong, Jian Lang, Ting Zhong, Fan ZhouAbstract
Personalizing Multimodal Large Language Models (MLLMs) as intelligent assistants has recently emerged as an active research topic, where an MLLM is expected to go beyond generic, one-size-fits-all replies, and instead generate responses grounded in user-specific objects, entities, and concepts encountered during interactions. Nevertheless, existing studies mainly focus on personalizing MLLMs on a static, predefined set of personalized concepts and require users to manually and frequently extend this set to accommodate newly emerging concepts, which is infeasible in dynamic-world scenarios. To address this limitation, we recast conventional MLLM personalization as an Open-Set problem, and propose TAME-O, the first long-context open-set personalized MLLM assistant. Specifically, TAME-O introduces a training-free, plug-and-play Concept Reconciliation Skill (CR Skill). It enables the assistant to automatically unlock novel concepts during prolonged human-MLLM interactions while preventing confusion with previously unlocked ones, allowing the MLLM to continually grasp more and more concepts and progressively refine the modeling of known ones. Extensive experiments under the open-set personalization setting underscore the efficacy of our method.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14118
PDF
-
Looking One Step Ahead: An Anticipation-guided Agent for Object State Readout in Videos
2026-11-10 14:05:39Yuanhe Tian, Yan SongAbstract
Understanding the progress of an activity requires tracking how the objects involved change over time. Object state readout provides this information by describing a target object's states and transitions across video frames. Although multimodal large language models (MLLMs) generate detailed visual descriptions, these descriptions may leave the attributes needed to distinguish successive states insufficiently specified. In this paper, we propose look-ahead state readout (LASER), an anticipation-guided agent for object state readout that uses possible next-step changes to determine which attributes to inspect in the present. Given temporally ordered frames and a target object, LASER converts anticipated changes into targeted visual questions and inspects the current frame to establish attribute values. It then checks state readouts and forecasts against independent observations of subsequent frames, refining a state record used to generate the final description. Reusable textual observation skills guide this process and are refined by tracing discrepancies with reference captions to the responsible instructions. Candidate revisions are selected on separate videos based on improved caption quality without increased contradictions with reference facts. Model parameters remain frozen throughout adaptation and inference, and the revised skills remain fixed during evaluation. Experiment results and further analysis on OSCaR and PLM RCap show consistent improvements of LASER over strong baselines and existing approaches, which demonstrates the effectiveness of our approach.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14113
PDF
-
ProofCoder: Continuous Reasoning for Automated Software Verification
2026-11-10 13:59:49Martim Afonso, In\^es Lynce, Maurizio Morisio, Jo\~ao F. FerreiraAbstract
Formal verification using proof assistants provides strong correctness guarantees for software, but constructing proofs remains labor-intensive and requires significant expertise. Recent approaches based on large language models (LLMs) have shown promise in automating proof synthesis. However, these approaches typically constrain the model to a rigid tactic-generation loop, in which the surrounding system controls premise retrieval, proof-state management, and backtracking. We introduce ProofCoder, an agentic proof-synthesis system for Rocq that approaches theorem proving from a coding-agent perspective. Rather than generating tactics within a fixed loop, ProofCoder reasons continuously throughout proof search and uses proof-assistant feedback to decide when to gather additional information, inspect proof states, revise previously generated proof fragments, or backtrack to an earlier point in the proof. This allows it to iteratively construct, repair, and refine proofs, at either tactic-level or whole-proof granularity. We evaluate ProofCoder on 280 challenging verification tasks from the AutoRocq Benchmark. On the best-performing configurations, ProofCoder increases proof success from 47% to 60% over the state-of-theart AutoRocq system, corresponding to a 27.7% relative improvement at approximately half the cost. Our ablations identify continuous reasoning as a key design choice: without it, the agent solves fewer lemmas at substantially higher cost, backtracks four to six times more often, and more frequently discards its own revisions. Whole-proof and tactic-level generation achieve similar success rates but follow distinct search and repair strategies. These results suggest that effective automated software verification requires more than improved tactic selection: continuous reasoning and feedback-guided proof revision are critical ingredients for robust proof synthesis.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14106
PDF
-
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
2026-11-10 13:47:29Tomer SolbergAbstract
We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.14083
PDF
-
Where Do Vision-Language Models Get Left and Right? Position-Code Counterfactuals in Qwen2.5-VL, Qwen3-VL and InternVL3
2026-11-10 13:25:38Enhao Cui, Junzhi Yang, Yaoshun Lin, Yuhan Feng, Zijian ChenAbstract
A vision-language model may take left-right direction from the orientation of image content within patches, its vision transformer's (ViT) position code, or token positions and order in its language model (LLM). Ablations show the ViT code is necessary; we test sufficiency by mirroring only a position code. In Qwen2.5-VL-7B, Qwen3-VL-4B and InternVL3-2B, mirroring ViT width positions reproduces the flipped-image answer on 84.3-93.2% of CV-Bench left-right questions (Qwen2.5-VL-3B: 87.5%, partly a left fallback). With two options, this also counts disruption; a half-grid shift flips most answers too. With the ViT code intact, LLM-side id and token-order mirrors change few left-right answers in all three series (a weak id test in Qwen2.5-VL). In Qwen2.5-VL-7B the effect sits in the global-attention ViT blocks, mostly the last. On What'sUp, flipping content and token order, not the position code, keeps more on/under than left-right answers at the flipped-image answer. Post hoc analyses qualify these results. On CV-Bench items with located objects, random permutations flip 18.9-31.0 points more answers when reversing the objects' order than when keeping it. On What'sUp, in Qwen2.5-VL and Qwen3-VL, the share of the left-right changes made by random permutations that land on the mirror relation is mostly below chance. Counted as returns to the original answer, the What'sUp contrast of support with left-right relations is clear only in InternVL3-2B. Most remaining errors give the same relation whichever object is asked about, suggesting that repair may target relation binding, object localization or use of the reference object.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14060
PDF
-
HandsOnAid: Building and Evaluating an Offline First-Aid Assistant for Emergency Response Scenarios
2026-11-10 13:25:28Rezwan Islam Salvi, Saiyma Sittul Muna, Mushfiqur Rahman MushfiqueAbstract
Emergencies can occur where there is no phone signal and no ambulance nearby. A small language model on a phone can be helpful in such situations, but its advice needs to be safe and accurate. We built HandsOnAid, a 4-bit Gemma 2B model fine-tuned with QLoRA on FirstAidQA dataset, a corpus of 5,550 first-aid question-answer pairs. We compared seven configurations, including the base, 4-bit and 8-bit fine-tuned models, and versions with a length floor, safety gate, or retrieval. We used a 41-pair question-answer bank with medically reviewed references that followed ANZCOR guidelines, and a strict 0-5 score rubric, with twelve safety overrides. Four frontier LLM judges (GPT-5.6 Sol, Claude Opus 5, DeepSeek V4 Pro, GLM-5.3) blindly scored every answer, with 45 hidden controls used to check judge reliability. Fine-tuning improved the mean score by +1.08 over the base model to 2.34. The best configuration scored 2.51 out of 5 which was the fine-tuned 4-bit model with retrieval. A medical professional also conducted a blind evaluation of 40 answers across the base, the 4-bit fine-tuned, and the retrieval configurations, and the scores were similar to the LLM judges' average scores. A keyword audit found limited coverage of several details of ANZCOR guidelines in the training corpus, that are required by the rubric, which suggests that missing information in the training data could be a cause of the low scores. On a smartphone device (Pixel 7 Pro) with six CPU threads and no network connection, the 4-bit fine-tuned model produced its first displayable text in 6.86 seconds and a complete answer in 14.88 seconds on average over ten questions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14059
PDF
-
Few-Step Streaming Video Generation via Condition Shifting
2026-11-10 13:01:20Deyuan Liu, Jungang Li, Kaiwen Zheng, Kai Jiang, Jintao Chen, Yaole Wang, Ming Lin, Tao Lin, Jianfei Chen, Jun Zhu, Jintao ZhangAbstract
Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to streaming video by using condition shifting to estimate the velocity field of the generated distribution within the generator. The original text condition selects generation, while a shifted condition selects fake estimation using the same parameters. This removes the independent fake network while retaining S2-Avatar's frozen reference teacher, Self-Replay Forcing, and perceptual regularization. We evaluate APEX on 180-second videos using three backbone evaluations per block and a one-step spatial Refiner, with a 70-case human study and a 320-case StreamAV-Bench comparison. Compared with S2-Avatar, APEX achieves higher video instruction fulfillment on the Progressive track (3.856 versus 3.831) and higher visual aesthetics across both tracks (0.641898 versus 0.632606). Human raters favor APEX most strongly on instruction following, with +30.0% net preference, followed by consistency and video quality at +4.3% each. Motion quality favors S2-Avatar, audiovisual synchronization is predominantly tied, and usability is unchanged. Separate measurements under matched training settings show 4.4% lower peak allocated GPU memory per GPU and 9.2% shorter mean iteration time than DMD.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14033
PDF
-
Program-Aided Patchable Skill Evolution
2026-11-10 12:53:12Jiahao Wang, Yuqi Xiong, Qing Yang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yubin BaoAbstract
Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based on downstream task feedback. However, existing methods primarily represent skills as natural language documents, intertwining procedural logic with descriptive knowledge and making skills difficult to maintain and evolve. To address this limitation, we propose PASE (Program-Aided Patchable Skill Evolution), a program-aided framework that iteratively evolves skills by associating them with executable programs. Unlike prior approaches that encode trajectory-derived experience primarily in natural language, PASE separates reusable procedural logic into editable programs, enabling targeted updates to executable components while reducing the need to repeatedly revise natural language skills. Extensive experiments across diverse models and benchmarks demonstrate that PASE consistently outperforms all baselines, by achieving over 2.8% improvements. Further analyses show that PASE exhibits greater evolutionary stability and generalisation capability, highlighting the critical role of programmatic knowledge in skill evolution. We will release all data and code via GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14019
PDF
-
Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception?
2026-11-10 12:22:34Liwei Liu, Jun Tao, Xingyuan Li, Xuenan Xu, Chen Zhang, Junyi Wang, Boya Zhang, Xiaoyu Yang, Zhen-Hua Ling, Wen Wu, Chao ZhangAbstract
Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope remains largely human-centric, focusing on what humans can directly see or hear. This progress raises the prospect of perception beyond human limits, such as extending hearing to sounds that are inaudible to humans. More broadly, the physical world is full of waves, vibrations, and oscillations, only a small fraction of which are directly audible to humans. This invites the extension of multimodal LLMs toward a broader form of machine hearing, which remains largely underexplored. To investigate this direction, we introduce the Machine Hearing Benchmark (MHB), comprising 6,128 instances across 13 tasks and seven domains. MHB spans highly heterogeneous input regimes, with sampling rates from approximately $10^{-5}$ to $10^6$ Hz, sequence lengths from $10^1$ to $10^6$ samples, and both single- and multi-channel inputs. Evaluations of current open-source and proprietary Audio LLMs (ALLMs) reveal limited zero-shot transfer to machine hearing. Supervised adaptation on machine-hearing data alone does not close this gap, suggesting that the challenge extends beyond data exposure to a systematic mismatch between existing audio front ends and machine-hearing inputs. To address this mismatch, we introduce MachEar, a lightweight encoder extension that complements the pretrained Audio LLM for machine-hearing inputs. The results show that MachEar equips a pretrained Audio LLM with stronger machine-hearing capabilities while largely preserving its existing audio understanding performance.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10693
PDF
-
Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies
2026-11-10 12:04:54Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert StahlbockAbstract
Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13966
PDF
-
From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses
2026-11-10 11:52:40Simon Hegelich, Bardh Prenkaj, Habiba Sarhan, Morteza Shahrezaye, Kolja Hegelich, Christian Montag, Ralf Schneider, Erik CambriaAbstract
AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary injects instructions into retrieved content, dual-use binaries such as bash, curl, and find become the payload. We argue that security in agentic systems is a structural property of the cognitive architecture and permission composition rather than an emergent property of individual models. Static regex blacklists miss structural evasions, whereas LLM-as-a-Judge guardrails incur high latency while over-blocking benign work. We present ActiveSecHarness, a neurosymbolic reference-monitor architecture built around Separation of Intelligence and Authority. It combines (1) Macaroon-inspired HMAC capability tokens across four Trust and Authority Rings, (2) a 2D product taint lattice $\mathcal{L} = \mathcal{L}_{\mathrm{trust}} \times \mathcal{L}_{\mathrm{sens}}$ and a workspace provenance ledger that prevents secret laundering across disk, (3) deterministic Ring-0 OS/tool guards, and (4) bytecode certificates, split-horizon audit logs, self-healing security test synthesis, and an adaptive UserWikiManager. Across $N=252$ fixtures ($120$ attack, $120$ benign, $12$ kill chains), a live local LLM judge (qwen3:4b) refuses $98.3\%$ of benign work at $142.3\,\mathrm{ms}$ latency, whereas Ring 0 achieves $\mathrm{ABR}=1.000$ and $\mathrm{FPR}=0.000$ in $12.7\,\mu\mathrm{s}$ ($11{,}200\times$ faster). In a multi-step trajectory ablation, an oracle Conseca-style stateless policy misses $4/12$ kill chains ($\mathrm{ABR}=0.667$) and coarse Boolean taint blocks $83.3\%$ of benign workflows, while our 2D product lattice achieves $\mathrm{ABR}=1.000$ and $\mathrm{FPR}=0.000$ at $\approx 20\,\mu\mathrm{s}$ per step.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13960
PDF
-
TreeAgent: Structure-Aware Memory Agent for Processing Long Hierarchical Data
2026-11-10 11:33:05Wei Gu, Weiwei Qi, Jiajun Tang, Tianhang Zheng, Bo Chen, Zhibo Zhang, Jinfei Liu, Kui RenAbstract
Practical Web applications increasingly require agents to interpret long conversations or documents. For inputs exceeding the context windows of large language models (LLMs), memory agents process segments sequentially and retain past information in bounded memory. However, they typically divide inputs into flat token segments without preserving structure or hierarchy, causing three limitations for structured data such as API responses or HTML documents. First, fixed-length segmentation can split fields of the same record, breaking their relationships. Second, segments lack hierarchical information, obscuring their structural context and positions. Third, successive memory updates may discard details of earlier sibling records needed for reasoning on later segments. To address these limitations, we propose TreeAgent, a structure-aware agent that uses the input hierarchy to guide both segment-wise context processing and access to past information. Specifically, TreeAgent constructs segments from complete subtrees and groups of adjacent sibling subtrees to preserve local structural relationships. We provide theoretical guarantees on segment counts to guide token budget selection toward matching the segment count of fixed-length segmentation. We further attach structural paths to the segments for the agent to identify their ancestors and hierarchical positions. We also introduce residual memory links from the segments of low-level children to the segments of high-level parents, enabling direct information flows beyond successive memory updates. We evaluate TreeAgent with four representative memory agents on eight retrieval and aggregation tasks. The inputs are derived from real-world application data in JSON, HTML, YAML, and JavaScript and range from 8K to 1M tokens. TreeAgent improves the average score across the four datasets for all four agents, with 3.61% performance gain on average.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13946
PDF
-
FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders
2026-11-10 11:21:43Ziwei Wu, Jingrui HeAbstract
Large language model (LLM) recommenders can produce semantically different recommendations when a user's protected attribute changes, even if the interaction history remains fixed. Controlling this disparity is challenging when model weights and full-vocabulary logits are inaccessible. We propose FAIDER (Fairness-Aware Item-level DEcoding for Recommendation), which incorporates fairness into list construction by selecting complete item candidates rather than manipulating token-level logits or repeatedly repairing finished outputs. The central idea is to separate the operational criterion for a violation from how strongly generation is constrained. Conformal-inspired empirical calibration fixes a cross-group semantic-disparity threshold, while online decoding applies either hard filtering or a soft penalty adjusted through dual-inspired feedback to target a prescribed violation rate. Separately, we establish a pathwise guarantee: under a uniform enforceability assumption, the soft decoder's empirical violation rate exceeds its target by at most $O(1/T)$. Experiments across recommendation benchmarks and LLM backbones show that Soft FAIDER improves both measured semantic fairness and ranking quality over the evaluated prompt-repair baselines. It also generally achieves a more favorable fairness-utility balance than the hard variant, indicating that stricter per-recommendation constraints do not necessarily yield lower measured disparity.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10285
PDF
-
TAPCO-G: LLM-Guided Design-Adaptive Timing and Power Co-Optimization with Graph-Based Physical Priors
2026-11-10 11:19:50Wuqian Tang, Zixiao Wang, Che-Chien Lin, Fong-Hua Fu, Laura Ang\'elica Shion-Korsak, Xinyun Zhang, Bei Yu, Chun-Yao WangAbstract
Post-placement timing and power co-optimization is critical to meeting setup timing targets and reducing power within placement constraints. A cell replacement can improve timing along one path while increasing power or reducing slack on others. Conventional optimizers follow fixed rules for scheduling and accepting repairs, limiting their ability to address design-specific bottlenecks. A large language model (LLM) can propose changes to these rules, but on its own it cannot reliably estimate how a cell replacement affects endpoint slack and power. TAPCO-G combines LLM-guided optimizer adaptation with graph-based physical priors to evaluate candidate cell replacements. The outer loop tunes tool settings using physical-design feedback and revises executable repair policies when tuning stalls. The inner loop anchors delay estimates to static timing analysis snapshots, accounts for upstream driver-load changes, and propagates delay shifts to timing endpoints. It combines these estimates with coarse-to-fine power screening to prioritize candidates for physical trials. TAPCO-G produced placement-legal, logic-equivalent implementations and outscored CERBERUS on all eight ASAP7 benchmarks from the MLCAD 2026 Contest, with a mean quality score gain of 5.516 points, and scored 21.648 points higher than TAPCO on average. These results demonstrate the effectiveness of the proposed co-optimization framework.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13931
PDF
-
Beyond Proxy Metrics: MLLMs as Human Surrogates for Explainable AI Evaluation
2026-11-10 11:15:28Eoin M. Kenny, Salim I. Amoukou, Tom BewleyAbstract
Explainable AI (XAI) has expanded into a broad and impactful research area, but the fundamental question of how best to evaluate explanation techniques has proven frustratingly elusive. Methodologies typically revolve around either proxy metrics which tell us little about the utility of an explanation, or human evaluation which---while generally considered the gold standard---is expensive, difficult to scale, and challenging to reproduce. In this paper, we investigate if Multimodal Large Language Models (MLLMs) can act as surrogate human participants to automate the evaluation of XAI. To do this, we first propose a ``purpose-grounded'' evaluation framework with metrics applicable to both MLLMs and human users alike. Then, we offer some conceptual insights as to why and when we can trust these models to automate this process. Lastly, we conduct extensive empirical testing across five purpose-grounded areas such as model improvement and fourteen popular MLLMs. Results indicate that all models trend positively, but OpenAI and Qwen models generally show higher alignment compared to other variants, which would be the recommended choices in practice. We expect our insights not to replace user testing, but rather to help XAI researchers complement their current evaluation methodologies and move the field away from heavy reliance on proxy metrics for measuring explanation utility.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13926
PDF
-
From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations
2026-11-10 11:05:19Vojtech Cahlik, Amir Reza Mohammadi, Rodrigo Alves, Pavel Kordik, Eva ZangerleAbstract
Recommender systems increasingly influence what users discover and consume online, yet the decision logic behind their outputs often remains opaque. Counterfactual explanation (CFX) methods provide an effective way to show which changes to a user's interaction history would alter a recommendation. In recommendation settings, however, CFXs often require many edits, producing long, low-level lists that are hard for users to interpret. Moreover, most evaluations emphasize edit counts while largely overlooking whether the resulting CFXs are coherent and actionable for users. We argue that this gap between generating valid CFXs and communicating model behavior stems from the lack of user-centered abstraction and limited qualitative evaluation. To bridge this gap, we investigate large language models as mediators that summarize raw CFX interaction edit lists into concise natural language explanations describing higher-level preference patterns. We optimize these mediators for correctness, informativeness, and linguistic quality through preference optimization, and evaluate the resulting explanations with human-calibrated metrics derived from separate human-labeled datasets. On the MovieLens-1M dataset, across multiple counterfactual generators and language models, the resulting summaries achieve high overall linguistic quality, while the strongest semantic results are obtained with high-success CFX methods such as ACCENT and SPINRec. Direct Preference Optimization improves the semantic metrics in almost all evaluated settings.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13914
PDF
-
Beyond Passive Imitation: On-Policy Mid-Training Distillation for Language Models
2026-11-10 10:15:20Ruize Zheng, Xuyang Liu, Siyu Ren, Xiaobing Tu, Yinggui Wang, Jinkui Ren, Xiantao Zhang, Linfeng ZhangAbstract
Continual pre-training (CPT) adapts large language models (LLMs) to specialized domains, yet its standard next-token prediction (NTP) objective treats every corpus token as a fixed target, regardless of its utility to the current model. In a controlled study on the same 1B-token mathematical corpus, we observe sharply different outcomes across base models: NTP improves Llama-3.2-3B's performance on mathematical benchmarks but substantially degrades Qwen3-1.7B-Base's performance, indicating that, under a fixed training recipe, the same training sequences can have model-dependent effects. To address this problem, we introduce On-Policy Mid-Training Distillation (OPMD), which reformulates mid-training from offline text imitation into active, query-driven knowledge acquisition. At selected anchor positions, OPMD samples trajectories from the evolving student policy and applies dense token-level reverse-KL rewards from a frozen teacher, training the model on states it actually visits rather than only on ground-truth prefixes. This on-policy objective reduces the training-generation mismatch of teacher-forced NTP. On MATH-500 and Minerva, OPMD improves the Qwen student over its base performance and outperforms the evaluated NTP baseline, which degrades on both benchmarks. OPMD integrates into CPT pipelines without added inference-time overhead and offers a model-aware alternative to passive domain adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13855
PDF
-
Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics
2026-11-10 10:11:30Bastien Dussard (LAAS-RIS, LAAS), Aur{\'e}lie Clodic (LAAS-IDEA, LAAS-RIS, LAAS), Guillaume Sarthou (LAAS-RIS, EPE UT, LAAS)Abstract
While symbolic reasoning for task allocation requires grounding a robot's physical capabilities, standard Unified Robot Description Format (URDF) files provide only low-level kinematics without the formal semantic context needed for reasoning. We present URDF2Ontology, an automated, taxonomy-agnostic neurosymbolic framework that transforms raw URDF files into populated, grounded OWL ontologies. It leverages a Large Language Model (LLM) for targeted semantic reasoning, coupled with an iterative sequential graph-purging mechanism to prevent context window saturation. To process complex kinematic structures, it employs a morphology-aware dual-track architecture featuring a bottom-up Tree Track for branching assemblies and a top-down Chain Track for serial limbs. Guided by neurosymbolic guardrails, the framework extracts functional sub-graphs and asserts populated ontologies aligned with arbitrary user-provided taxonomies. Empirical evaluation across a diverse fleet of heterogeneous robots demonstrates strong schema alignment, valid structural extraction, and a significant reduction in manual domain authoring overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13850
PDF
-
WarBias: A Bilingual LLM Benchmark of Stereotypes About Internally Displaced People and Veterans
2026-11-10 10:05:09Viktoriia Makovska, Tetiana Zakharchenko, Oleksandra OstafiichukAbstract
This paper contains examples of stereotypes about veterans and displaced people that may be offensive or distressing. Social bias benchmarks for language models commonly examine categories such as gender, race, and religion, often drawn from lists of legally protected characteristics. Veterans and internally displaced people (IDPs) fall outside these lists, and stereotypes about them, which can undermine access to employment, housing, and social participation, remain largely absent from language model evaluation. We introduce WarBias, a Ukrainian-English benchmark of stereotypes about these two groups. Built from a taxonomy of 120 stereotype claims grounded in research and monitoring reports, WarBias contains 1,007 stereotype-counter-stereotype-unrelated sentence triplets and 240 multiple-choice questions per language. A Ukrainian language model selected in a blinded human pilot generated the Ukrainian triplets. At least two independent annotators reviewed each triplet in the annotation cohort. The authors revised items in response to the reviews, and the final release was machine-translated into English. Each claim carries a human severity rating. In a baseline evaluation of six models, four prefer stereotypical Ukrainian sentences about at least one group, most strongly about IDPs, while English scores are mostly balanced. WarBias supports complementary evaluations of stereotypical preferences and context-sensitive judgments, and provides paired forget/retain material for unlearning-based bias mitigation. We document the benchmark's construction, intended uses, and limitations, and offer its construction method as a template for analogous benchmarks in other conflict-affected societies.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11284
PDF
-
PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard
Abstract
Typed-decision encoders answer a question about a text in one forward pass, but their behaviour outside English is rarely measured on a fixed yardstick. We release PolyRoute: 322 native-language support messages in 12 languages and 9 writing systems, 156 code-mixed or romanised messages (Hinglish, Spanglish, Arabizi), 967 optional native training rows, and a protocol for a three-way department-routing decision. Labels come from Qwen3.8-27B with a blind second pass (91% of candidates kept); an independent model, gemma4-31b, agrees on 97.2% of test items, and the largest character 5-gram similarity between any test text and any training text is 0.33. A leaderboard of 13 systems gives 61.2% for the English-root checkpoint, 77.3% for the shipped multilingual one and 96.6% for the best fine-tune; TF-IDF with logistic regression reaches 91.9%. On four withheld languages the three multilingual systems score 77%, 90% and 93%. On code-mixed text the English root (85%) is nominally ahead of the shipped multilingual checkpoint (79%; p=0.134). The split resolves differences only above about 4 points. All texts and labels are LLM-generated.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13843
PDF
