Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Wednesday 14 October · still arriving

Computation and Language

More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training

Haoyuan Wu, Aoqi Wu, Jiani Hu et al. (+1 more)

Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual inputs. However, how visual signals shape scaling behavior and support capabilities beyond visual understanding remains unclear. We investigate this question through controlled visual-content ablations across model sizes and training budgets. Specifically, we replace image embeddings with content-free padding token embeddings. Retaining visual content improves text prediction on image-text examples without materially changing the lowest text-only loss at a given compute budget, the optimal balance of model size and training data, or aggregate language scores. The relative multimodal loss benefit grows approximately as a power law of compute. To test benefits beyond understanding images, we evaluate spatial reasoning from text descriptions alone. Both conditions improve with model and data scaling. During training of the largest model, visual gains are most sustained in localization, navigation, and symbolic planning, which involve maintaining object configurations or composing spatial updates; gains in spatial relations, geometry, and physical commonsense are less consistent. These findings identify visual content as a scalable anchor for multimodal learning, with benefits that extend beyond visual inputs while preserving aggregate language performance.
Read the full abstract

All authors Haoyuan Wu, Aoqi Wu, Jiani Hu, Bei Yu

Computation and Language

How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs

Shuyuan Zheng, Yun-seo Lee, Xing Gao et al. (+7 more)

Legal reasoning is a fundamental capability for large language models (LLMs) to complete legal AI tasks such as legal judgment prediction. In legal practice, this reasoning is shaped by legal philosophy: a judge's view of the nature and sources of law guides how legal materials are interpreted and applied, so judges working from the same statutes and precedents can reach different judgments. Existing research has largely overlooked whether LLMs can understand legal philosophy and apply it in legal reasoning, an ability we call legal-philosophical reasoning. To fill this gap, we introduce LePhilBench, a benchmark for evaluating the legal-philosophical reasoning of LLMs that comprises two benchmarking tasks and a dataset. The two tasks evaluate how well LLMs understand legal philosophy and how well they apply it in legal reasoning, respectively. The dataset is manually and meticulously constructed. Its test set contains 220 U.S. Supreme Court opinions. A law professor designed fourteen annotation questions on legal philosophy, and three law-trained annotators with formal training in jurisprudence answered all fourteen questions for every opinion, yielding 9,240 legal-philosophical labels. LePhilBench takes the first step toward exploring legal-philosophical reasoning in LLMs.
Read the full abstract

All authors Shuyuan Zheng, Yun-seo Lee, Xing Gao, Jialu Wu, Jiabao Hu, Katrina Qiyao Wang, Xinbo Lin, Qianying Liu, Chuan Xiao, Tao Huang

Computation and Language

ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models

Zhaoyan Jia, Chengwei Zhou, Gourav Datta et al. (+1 more)

Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation can suffer from entropy degradation, which narrows the reasoning paths available for exploration. Recent work mitigates this issue by applying standard GRPO with left-to-right generation. However, independently generating every rollout from the input prompt can leave alternative continuations from intermediate states underexplored, while trajectory-level advantages assign uniform credit to all tokens without distinguishing the contributions of individual reasoning segments. We propose ForkGRPO, an RL framework that couples efficient exploration with fine-grained segment-level credit assignment. It samples multiple continuations from high-entropy intermediate states along a reference trajectory, prioritizing textual boundaries and reusing shared prefixes. The continuations provide complementary learning signals: within-state group-relative advantages guide which continuations to reinforce, while Monte Carlo state-value differences indicate which reasoning segments improve expected outcomes. Among the evaluated architecture-preserving RL methods, ForkGRPO achieves the best performance on three of four benchmarks, while improving over the directly comparable JustGRPO by up to 1.2 percentage points and using up to 27.8% fewer generated tokens. ForkGRPO-Fast further achieves a $2.49\times$ training wall-clock speedup with negligible accuracy loss.
Read the full abstract

All authors Zhaoyan Jia, Chengwei Zhou, Gourav Datta, Massoud Pedram

Computation and Language

Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers

Josh Barua, Kyle Mahowald and William Rudman

Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases–e.g., a "blind faith in text"–but why preferences vary across models, domains, and input conditions remains unclear. We develop a predictive account from a Bayesian perspective, positing that VLMs combine conditionally independent evidence from each modality with prior beliefs, subject to modality-specific biases. The resulting two-parameter cue combination model accurately predicts VLM preferences under unseen combinations of input degradation and transfers to new forms of unreliability without refitting. Separating evidence strength from integration bias explains how VLMs can follow text even while weighting visual evidence more heavily, reconciling reports of text and vision dominance under a single combination rule.
Read the full abstract

Computation and Language

KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?

SungHo Kim, Eojin Jeon and SangKeun Lee

Korean neologisms arise through diverse mechanisms, a demanding test of language models beyond lexical memorization. To enable systematic evaluation, we introduce NeoTrace, an automated, rerunnable framework that collects and dates neologisms across genres. Its 4,271 entries support KoAGE, a cutoff-aware benchmark with three acquisition and two generation tasks—the latter, to our knowledge, the first to compare model coinages with attested neologisms under their original materials and community context. Across 21 models, lexical recall diverges from contextual inference: in a five-model temporal analysis, models define only 13-30% of cutoff-year words, yet can infer meaning from one usage. However, structural understanding remains limited: even correct definitions barely improve formation analysis of pre-cutoff neologisms. Given word-building materials, single models often follow human formation mechanisms, whereas multi-agent coinage favors abbreviation and depends on interaction framing. KoAGE thus separates what models know, learn from use, and coin.
Read the full abstract

Computation and Language

ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies

Sangmin Lee, Yejin Jeon and David Ifeoluwa Adelani

Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresent much of the linguistic long tail. To address this gap, we introduce ELARSpeech, a large-scale multilingual speech resource comprising 30,202 hours of speech across 675 underrepresented languages, curated from the Endangered Languages Archive. Combining human-annotated and unlabeled recordings, the corpus spans diverse recording conditions, domains, and language families. Beyond corpus construction, our experiments show how ELARSpeech supports extending ASR and TTS capabilities to diverse underrepresented languages, with further benefits from pseudo-labeling unlabeled data. At the same time, our speech representation analysis reveals remaining limitations in transferring existing multilingual models to the linguistic long tail. Together, ELARSpeech provides both a resource and a testbed for extending multilingual speech technology further into the linguistic long tail. We publicly release the dataset, all trained ASR and TTS models, and the complete data construction pipeline to facilitate research on long-tail multilingual speech technologies.
Read the full abstract

Computation and Language

The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation

Lin Ai, Emma Thronson, Katherine Conhaim et al. (+1 more)

Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scores clearly, make diverse data available, or evaluate models directly on the task. This paper proposes PROPALIGN, a multiple-summary-based approach for propositional salience score estimation, and releases PROPALIGNBANK, an accompanying dataset for the method with 138K alignments of over 35K propositions. We compare several approaches to salient proposition extraction in English across a broad range of spoken and written genres, and demonstrate that naively asking models for judgments leads to inconsistencies. By contrast, graded, summary-based metrics are more stable. We further observe that while single models perform worse than humans, an ensemble of models incorporating linguistic features approaches manual annotation quality ceilings. In addition, analyses of the model outputs suggest insights into how models can extract salient information with and without the use of summaries.
Read the full abstract

All authors Lin Ai, Emma Thronson, Katherine Conhaim, Amir Zeldes

Computation and Language

Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback

Li Wang, Chen Zhang, Yirong Yang et al. (+4 more)

User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements. We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback. SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests. To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions. We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization. We construct a benchmark spanning five personalized writing tasks to evaluate cross-request generalization. Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.
Read the full abstract

All authors Li Wang, Chen Zhang, Yirong Yang, Xingyu Chen, Jinkun Zhao, Tianhao Peng, Wenjun Wu

Computation and Language

Evaluating Compressed Memory: Dependence, Utility, and Content Benefit

Minsu Oh, Seunghui Jwa, Chanjun Park et al. (+1 more)

Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's score without showing that it outperforms a model trained without memory. We combine zeroing with separately trained models that cannot access stored text or receive the same constant input for every document. Across nine systems, some models rely on memory yet perform worse than the trained alternative. For example, in experiments that predict states in generated stories, zeroing memory worsens a model's prediction loss, yet a model trained without memory achieves lower loss than the original model with intact memory. On TriviaQA, giving xRAG memory from another question's passage raises F1, which measures word overlap with accepted answers, from 19.38 without a document to 24.78. Its effect on how often outputs contain an accepted answer is statistically uncertain. The question's retrieved passage scores higher still (29.88 F1). Thus a gain over no document alone does not establish that the gain requires the question's passage. Evaluations must therefore specify the comparison model, absolute performance, and generation and scoring conditions.
Read the full abstract

All authors Minsu Oh, Seunghui Jwa, Chanjun Park, Yeo-Chan Yoon

Computation and Language

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

Thomas Zeng, Zelei Cheng, Mingyang Zhou et al. (+3 more)

Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving LLM agents is to use more capable expert models to provide training supervision, either by behavior cloning the expert's trajectories or by using the expert to correct the actions in trajectories generated by the weaker student model. However, expert LLMs can provide richer supervision than actions alone: they can directly generate textual critique that explain why specific actions are incorrect. We study whether training on such feedback benefits LLM agents and propose Critique-Augmented Agentic Fine-Tuning (CAFT), a framework that elicits textual expert feedback on student-generated trajectories. For each incorrect action, the expert yields both a corrected action and a textual critique explaining the student's mistake–which we then use as the training target for fine-tuning. Across four student models from the Nemotron 3 and Gemma 4 families on the agentic domains $\tau^2$-Bench Airline+Retail and WebShop, adding critiques to action-level supervision improves performance by 8% on average over action-only distillation. Additionally, CAFT checkpoints can also provide a better warm start for reinforcement learning than expert-trajectory distillation. Our results demonstrate that textual critiques can strengthen supervision for multi-turn LLM agents.
Read the full abstract

All authors Thomas Zeng, Zelei Cheng, Mingyang Zhou, Sambit Sahu, William Campbell, Genta Indra Winata

Computation and Language · Cross-listed from cs.AI

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Minghao Guo, Qingyue Jiao, Xiujin Liu et al. (+77 more)

Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a significant challenge as they move toward long-horizon tasks and lifelong settings. Addressing this challenge requires effective memory mechanisms that can maintain continuity across sessions, adapt to changing users and environments, and refine memory-management policies through accumulated experience. We introduce a two-axis analytical framework for multimodal agent memory structured around two key questions: how multimodal information is formed and represented (Axis I, Formation and Representation), and how its management adapts with accumulated experience (Axis II, Memory Management). Axis I, Formation and Representation, characterizes what information is retained and how it is encoded (e.g., modality-specific embeddings, textual and structured records, latent and parametric representations) to support subsequent reasoning and action. Axis II, Memory Management, distinguishes three tiers: T1 Static Memory reuses fixed memory; T2 Dynamic Memory updates memory through a stable policy; and T3 Self-Evolving Memory updates memory through an evolving policy. Based on this framework, we synthesize recurring design patterns and derive principles for balancing source fidelity with abstraction, maintaining temporal validity and provenance, grounding memory use in recoverable evidence, and evolving memory policies over time. Furthermore, we discuss the challenges and potential future directions for the memory mechanism of multimodal agents.
Read the full abstract

All authors Minghao Guo, Qingyue Jiao, Xiujin Liu, Jianhong Pang, Ruimeng Yang, Naihao Xu, Liwei Che, Haochen Xue, Ziqi Wang, Xinying Cai, Jiaxuan Luo, Jiaxin Deng, Xuesong Ye, Jintao Qu, Wenyao Gao, Jingwen Gu, Chenyang Zhao, Shichun Liu, Guibin Zhang, Zefang Liu, Siyin Wang, Wujiang Xu, Danrui Li, Zeru Shi, Woongyeong Yeo, Shuang Liu, Wei-Chieh Huang, Weizhi Zhang, Tianyu Yang, Kangsan Kim, Yebowen Hu, Bowen Wen, Bowen Jiang, Haohao Su, Ming Yin, Sheldon Yu, Mian Zhang, Yuyan Chen, Hanrong Zhang, Kai Mei, Zihao Zhang, Mingyu Jin, Xi Zhu, Hengyi Wang, Tianxin Wei, Linyong Nan, Zhenwen Liang, Zhendong Chu, Ziqi Huang, Yongye Su, Sixun Dong, Shujian Liu, Kaiqu Liang, Jiaojiao Han, Zhaoye Fei, Kun Wang, Shihan Dou, Zhichun Guo, Xingjian Diao, Zeqi Gu, Heng Wang, Tao Feng, Cheng Qian, Hamid Palangi, Silei Xu, Xi Yun, Yi Zhu, Shilong Liu, Qingsong Wen, Sung Ju Hwang, Zuxuan Wu, Yu-Gang Jiang, Yiyu Shi, Dimitris N. Metaxas, Jiaxuan You, Julian McAuley, Mengdi Wang, Jiawei Han, Philip S. Yu, Ziyi Ye

Computation and Language

Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems

Taro Yano, Yoichi Ishibashi and Masafumi Oyamada

Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood. We study Best-of-N as a competition between the extreme reward tails of correct and incorrect responses. This view shows that success depends not only on the probability of sampling a correct response, but also on whether correct responses dominate incorrect ones in the upper tail. Using extreme value theory, we characterize three asymptotic regimes: correct-tail-dominant, incorrect-tail-dominant, and critical explaining both monotonic gains and reward-hacking-induced degradation. We further derive finite-sample scaling laws for representative reward distributions, showing that, under Gaussian rewards, incorrect responses with sufficiently large variance can dominate selection even when their mean reward is lower. Unlike oracle selection, convergence with an incomplete selector can be polynomial rather than exponential. Finally, we propose a lightweight tail-tension criterion to estimate when additional sampling may become harmful. Experiments on synthetic data and real reward model scores are consistent with the theoretically predicted regimes, scaling laws, and diagnostic behavior, suggesting that tail competition provides a unified lens on Best-of-N sampling for verifiable problems.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement

Kyusong Lee, Heting Ying and Tiancheng Zhao

Embodied visual tracking requires a robot to identify a designated target from visual observations and control its own motion to follow that target through an environment. Following an isolated person is a comparatively simple demonstration of embodied visual tracking, but following the intended person among distractors remains challenging. Existing methods exhibit a substantial drop in success from single-target to distractor tracking, motivating a focus on the shared spaces that person-following robots must navigate. We present \method{}, a vision–language waypoint policy built around the hypothesis that visual and language representations should be aligned before tracking-specific motion is learned. The policy combines complementary frozen visual encoders, multiscale temporal context, a transformer backbone, and a lightweight head for robot-centric waypoint prediction. Its training progresses through vision–language alignment, multimodal reasoning mid-training, and tracking specialization on 19,532 oracle episodes. Compared with 41.54% distractor-tracking success for our earlier OmTrackVLA model, the complete multi-stage recipe achieves 55.80%. We then explore on-policy refinement using filtered oracle labels for states visited by the policy. This preliminary study adds 2.42 percentage points of distractor-tracking success, reaching 58.22%, while reducing collision rate by 1.99 pts. The final policy records the highest distractor- and ambiguous-tracking success rates among the compared methods. These results support staged multimodal learning as a promising direction for tracking among distractors and motivate further study of on-policy refinement for person following in shared spaces.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering

Weilun Xu and Zipeng Sun

Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it may act through a component shared with neighbouring behaviours, which unsteered and random baselines cannot separate. We introduce the competing-target test: a vector is compared with the vector built the same way for a competing target, and an equivalence test states when their difference is below a useful margin. We apply it in open-weight models to vectors for Kantian deontology, which judges an act by the rule it follows, and act utilitarianism, which judges it by the welfare it produces. On held-out situations, prompting a framework raises its score and lowers the other's, whereas vectors for either framework move both scores alike, and none reaches the margin. The two vectors share most of their direction, a request to apply some framework; the same construction separates an optimistic from a pessimistic tone, whose vectors share much less. What a vector shares with its competitors therefore sets what it controls: steering a perspective can deliver a mixture, and measuring a disposition can measure its neighbours, unless tested against the competing target.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents

Minchan Kim, Sungho Bae, Youngjin Kim et al. (+1 more)

Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tasks that require multiple interactions, rewards are given only upon successful task completion, making all-fail groups common early in training and limiting opportunities to practice later steps. Guide Assisted GRPO replays a successful reference prefix before the learner continues. We study how initial positions, handoff units, and movement rules affect unassisted task completion. Across three model sizes on BFCL, starting near completion is more effective under a fixed turn-level threshold rule. Finer handoffs alone do not consistently help, but outcome-informed tool-call selection outperforms GRPO on trained and untrained task categories. Guided starts also improve AppWorld success on both evaluation splits. These findings highlight where learning starts and how starting positions move as key curriculum choices.
Read the full abstract

All authors Minchan Kim, Sungho Bae, Youngjin Kim, Hyunwoo Park

Computation and Language

Target-Token Asymmetry Can Masquerade As Depth Specialization

Danlin Li, Miao Li, Xu Han et al. (+1 more)

Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger early-layer effect on one corpus as early-layer specialization for its task. Such a comparison averages over the tokens that each corpus asks the model to predict, and these target tokens differ: math solutions, for example, ask for far more whitespace and numbers than encyclopedia prose. We show that this difference can create the appearance of depth specialization. We split a cross-corpus early–late damage interaction by target-token type and recompute it under a target mixture shared by both corpora. Between GSM8K and Wikitext, a positive interaction replicates across five model instances. In the three fully decomposed models, only whitespace has a positive interaction. Removing whitespace reverses the pooled effect in all three, and matching the full target mixture reverses it in two. The diagnosis holds under position matching, adversarial reassignment of token types, and a continuous readout. The risk can also be anticipated from the tokenizer alone. A screen computed before any model runs places every held-out pair it scored in the region its label predicts, and on the pairs it rates at high or medium risk, removing whitespace reverses every positive pooled estimate. A smaller content-word effect one token ahead follows the share of content targets that the unablated model already predicts. A cross-corpus depth effect therefore supports an interpretation of task specialization only after the target-token mixture is reported, the effect is decomposed by token type, and a mixture-matched summary keeps its sign.
Read the full abstract

All authors Danlin Li, Miao Li, Xu Han, Jiecheng Lu

Computation and Language · Cross-listed from cs.LG

Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering

Hyojung Han, Jongmin Kim and Seung-Hun Jeon

A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those regions, so a gate-versus-random comparison does not isolate these mechanisms. We introduce Counterfactual Gate-Support Decomposition (CGSD), a four-arm, budget-matched design that crosses gate eligibility with support distribution and decomposes the observed gate effect into within-support selection, between-support redistribution, and their interaction. The practical constraint is finite-pool realizability: we characterize mass and token-assembly conditions under which the required arms can be constructed, together with a support-extinction case in which the ordinary design is undefined. On Korean-English and Korean-Japanese retrieval, the mean within-support selection component is the only one that exceeds its calibrated null band (+29.7 and +5.6 holdout items; 30/30 positive replicates), decisively in Korean-English and marginally in Korean-Japanese; redistribution and interaction remain unresolved at the available power. The same pattern holds for a second, unrelated gate family – a model-confidence threshold rather than a deterministic verifier – judged against its own null (+27.3 items, 9/9 positive), so the result is not a property of one gate's mechanism. On a mathematics gate, zero-eligibility supports leave the ordinary design undefined at every budget, while the extended design is constructible only inside narrow budget bands that an exhaustive scan locates and that the natural operating point misses – the assembly condition separating a property of the pool from a limitation of the packer. CGSD therefore returns a decomposition, a constructible-but-underpowered design, or an explicit non-constructibility result, and says which; it prevents support redistribution from being silently interpreted as sample-level gate quality.
Read the full abstract

Computation and Language

LLM-jp-4 Technical Report

LLM-jp: Chaoran Liu, Daisuke Kawahara, Hideyuki Tachibana et al. (+14 more)

This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usability. LLM-jp-4 comprises an 8B dense model and a 32B-A3B mixture-of-experts model, both trained from scratch on approximately 12 trillion tokens. To support independent verification and reproduction, we establish explicit criteria for selecting training data, external models, and software, and make the development process publicly available. Evaluation results demonstrate substantial improvements over previous LLM-jp models and competitive performance against open-weight models of similar scale. By documenting the development principles, training procedures, and empirical findings of LLM-jp-4, we aim to provide a reference for future sovereign AI development.
Read the full abstract

All authors LLM-jp: Chaoran Liu, Daisuke Kawahara, Hideyuki Tachibana, Hirokazu Kiyomaru, Jun Suzuki, Koshi Eguchi, Kouta Nakayama, Qianying Liu, Rio Yokota, Ryo Takahashi, Sadao Kurohashi, Sosuke Hosokawa, Taishi Nakamura, Takashi Kodama, Yun-Ang Wu, Yusuke Miyao, Yusuke Oda

Computation and Language

TopicMerge: A Divide and Conquer Approach to Topic Modeling

Matthew Raffel, Lizhong Chen, Sai Munikoti et al. (+1 more)

Recent advancements in topic modeling have split into two main paths: efficient embedding-based methods that offer scalability but are often outperformed on standard clustering metrics, and Large Language Model (LLM) approaches that achieve state-of-the-art clustering performance but at the cost of prohibitive computational expense and poor scalability. This paper introduces TopicMerge, a novel multi-stage pipeline that bridges these approaches to achieve both state-of-the-art clustering performance and computational efficiency. TopicMerge first employs an efficient clustering pipeline to deliberately over-segment a document corpus into a large set of fine-grained, semantically pure micro-clusters, which are then given initial semantic labels. It then introduces a novel, iterative merging algorithm where an LLM, guided by local neighborhood context, arbitrates on consolidating candidate pairs. These approved merges are then selectively executed and semantically relabeled by the LLM, hierarchically building broader, more coherent topics. Extensive experiments on the Bills and Wiki datasets show that TopicMerge achieves state-of-the-art clustering performance while reducing required LLM calls by over 92% compared to document-level methods, offering a practical and scalable solution.
Read the full abstract

All authors Matthew Raffel, Lizhong Chen, Sai Munikoti, Sameera Horawalavithana

Tuesday 13 October · still arriving

Computation and Language · Cross-listed from cs.GT

Truthful and Expected-Payment-Optimal Model Routing in Graph-Based Agentic Workflows

Jiayuan Liu, Mingyu Guo, Jiarui Gan et al. (+1 more)

Assigning routine tasks to cheaper large language model (LLM) providers can reduce generation cost, but switching providers may require processing accumulated context again. Keeping dependent tasks with the same provider can instead reuse eligible context. Graph-based workflows therefore couple routing decisions across tasks. Independent providers may also privately know their real-time unit costs and strategically misreport them. We formulate this routing problem as a single-parameter procurement auction and propose STAR (Strategy-proof Topology-aware Agent Routing), which minimizes virtual-cost-weighted graph workloads. Its allocation rule and payments, computed by integrating workload over possible cost reports, make truthful reporting utility-maximizing regardless of other providers' reports and cover each truthful provider's execution cost. With independent cost distributions and non-decreasing virtual costs, STAR additionally minimizes the user's expected total payment to providers. Controlled synthetic experiments separate the execution-cost benefit of topology awareness from the payment benefit of virtual-cost optimization: the former grows with fan-out and transferred payload, while the latter increases gradually along the tested prior-shape heterogeneity path. A paired sensitivity study quantifies how payment savings vary with prior misspecification while strategy-proofness is preserved.
Read the full abstract

All authors Jiayuan Liu, Mingyu Guo, Jiarui Gan, Vincent Conitzer

Computation and Language

PersEvalBench: Can LLM Evaluators Judge Contextually Appropriate Use of Persona Information?

Xinyi Liu, Hooshang Nayyeri, Emine Yilmaz et al. (+3 more)

Large language model (LLM) evaluators are increasingly used to assess personalized assistants, yet whether they can reliably judge personalization has rarely been tested. We introduce PersEvalBench, a benchmark testing whether an evaluator can recognize appropriate and inappropriate uses of user history. It contains 403 multi-episode scenarios where user information should persist, transfer, or cease to apply. The benchmark covers nine controlled error subtypes across three families: under-personalization, over-personalization, and misapplied-state errors. Human audits confirm that generated errors match their intended types and that the prescribed uses of user information are reasonable. Across five LLM evaluators, recognition of controlled personalization errors remains limited even with the full dialogue history. On the human-evaluated subset, under-personalization shows the largest gap: humans recognize 94.4% of these errors, compared with 63.9% for the strongest reported evaluator. Evaluators often recognize that a response is problematic but reverse the error direction, mistaking failure to follow an applicable preference (UNDER) for use of an inapplicable preference (OVER). Easier evidence access offers little help: highlighting the relevant history turns raises error recognition only slightly, suggesting that the remaining difficulty lies in judging what role that information should play in the response.
Read the full abstract

All authors Xinyi Liu, Hooshang Nayyeri, Emine Yilmaz, Dilek Hakkani-Tur, Charith Peris, Hari Thadakamalla

Computation and Language

Qwenfant: Train Big Character-level BabyLMs on Concise Parallel Text

Lukas Edman and Alexander Fraser

This work concerns our submission for the Multilingual track of the 2026 BabyLM Challenge. We improve on our baseline using data that has been summarized and translated by an LLM, showing that higher-quality data can come from synthetic sources. We further improve with 2 simple changes: using a larger model, and using a character-level vocabulary. Both of these changes require LoRA-style fine-tuning for realizing their full potential. We dub our final Qwen3-based model Qwenfant, which, at the time of submission, ranks 1st in the Multilingual track.
Read the full abstract

Computation and Language

Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance

Lucas H. McCabe, Sarah Lukens and H. Howie Huang

In so-called "Industry 4.0," integrated sensors, analytics tools, and other digital technologies supplement industrial workflows, potentiating enhanced visibility and automation. Prognostics and health management (PHM) and natural language processing (NLP) practitioners alike have explored the application of large language models (LLMs) to industrial asset management, but many prior works' focus on exam-like benchmarks has limited their assessment of LLMs' ability to automate practical operations. Herein, we introduce CoffeeBench, a fault diagnostics task for LLM agents, using a simulated appliance. The LLMs we evaluate struggle to consistently identify faults from the sensor information alone, but the best-performing ones can iteratively refine the fault-option space to eventually obtain a successful diagnosis. Our subsequent analyses, therefore, focus on: differentiating models by diagnostic efficiency (RQ1); examining the lagging performance of the three worst models (RQ2); and identifying viable heuristics for selective prediction (RQ3), including that initial diagnostic uncertainty and LLM-judged soundness of reasoning are high-signal predictors of diagnostic success. In addition to our benchmark results (Section 3.1), we provide practical insights for improving the performance of the open-weight models on CoffeeBench, such as by explicitly tracking episode state on their behalf to reduce timeouts (Section 3.2) or applying a deliberation loop to refine diagnostic hypotheses (Section 3.3).
Read the full abstract

Computation and Language · Cross-listed from cs.CY

From Efficiency to Sufficiency: The Cost-Aware Measurement Design Framework for Automated Essay Scoring

Yi Gui

Compute cost in automated essay scoring (AES) is usually treated as a technical efficiency issue rather than a measurement design concern. Yet deployment decisions require more than reporting latency, model size, or inference expense. In high-stakes settings, total burden includes validation, monitoring, adjudication, compliance, and governance; in instructional settings, pricing, licensing, and integration may dominate cost. This paper reframes AES as a cost-constrained measurement system and introduces the Cost-Aware Measurement Design (CAMD) Framework, a four-layer structure consisting of metering, allocation, unit economics, and decision, for translating computational and workflow resource records into decision-relevant cost constructs. Direct cost is specified as monetary outlay plus attributable labor and time, and two criteria, design attribution and auditability, determine what the cost boundary excludes. Burdens that satisfy neither criterion, such as institutional capability and governance posture, are represented as constraints on which designs are admissible rather than priced. The paper defines cost per defensible score (CPDS) and argues that AES systems should be compared by quality-cost sufficiency: minimizing cost among defensible scoring designs that satisfy measurement requirements. Scoring volume conditions all four layers, so cost per defensible score is treated as a function of scale rather than as a single transferable number. CAMD provides a portable basis for representing, comparing, and evaluating cost across AES studies and deployment contexts.
Read the full abstract

Computation and Language

Whose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources

Mir Tafseer Nayeem and Davood Rafiei

Benchmarks shape how model capabilities are measured and interpreted, yet their scores can obscure whose conventions, contexts, and judgments define successful performance. We introduce a user-centric audit framework that distinguishes users who contribute benchmark content from those whose needs evaluation results are intended to represent. The framework operationalizes seven dimensions across benchmark content, metadata, documentation, and scoring procedures. Across 16 resources, we find that American-centered conventions account for 62.4-94.4% of matched signals in 11 text benchmarks, while geographic visibility in five image-text resources is concentrated and strongly associated with national GDP share (mean Pearson r = 0.780; Spearman p = 0.778). Documentation reveals a systematic source-target gap: all 16 resources operationalize source-user context, but none operationalize target-user context. Paired scoring experiments further show that meaning-preserving answer variants reduce DROP exact-match accuracy from 100.0% to 33.3%, while TruthfulQA exhibits metric-dependent reductions in reference similarity. Our framework and documentation checklist make user assumptions auditable, clarifying what benchmark scores represent and where evaluation claims are supported.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis

Bo Shao, Yihan Ma, Yiting Qu et al. (+2 more)

Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong dependence on contextual information make it difficult for platforms and moderators to detect and moderate them effectively. Moreover, existing moderation studies typically classify memes as safe or unsafe based on individual images, lacking the ability to perform broader provenance analysis, i.e., where a meme originates, how it spreads, what cultural symbolism it represents, whether it poses potential risks to society, etc. To bridge this gap, we introduce MemeTrace, a multimodal LLM-based agent that automatically traces the provenance and potential risks of emerging memes. We evaluate MemeTrace on Meme100, a dataset of 100 real-world memes, using both human annotation and automatic metrics. The results demonstrate that MemeTrace substantially outperforms the VLM baseline. More importantly, MemeTrace achieves higher accuracy in detecting unsafe memes, especially those involving disinformation and sensitive content, and remains robust under visual perturbations.
Read the full abstract

All authors Bo Shao, Yihan Ma, Yiting Qu, Michael Backes, Yang Zhang

Computation and Language

Copy-Paste Language Models

Nathan Godey and Yoav Artzi

Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can be improved through explicit modeling. We propose Copy-Paste Language Models (CPLMs), which add a lightweight Copy-Paste head to the conventional language modeling (LM) head. CPLMs improve training efficiency, downstream performance, and offer new operating points in long-context and retrieval setups. We validate our approach by pretraining models from 135M to 1.7B parameters, showing improvements across all scales and backbones with negligible training and inference overheads. We explain the success of CPLMs by showing that they partially mitigate the LM head gradient bottleneck through an alternative gradient path.
Read the full abstract

Computation and Language

Do Syntax Heads Influence Model Behavior?

William Timkey and Tal Linzen

Transformer language models develop attention heads that specialize in syntactic relations, for example, attending from verbs to their subjects. Do these heads play a causal role in the model's syntactic predictions? Evidence for such a role is mixed to negative: even when we force these heads to attend to a distractor noun other than the subject, the model's syntactic predictions are still more consistent with the subject than with the distractor. Interventions on specialized syntax heads had a significantly stronger effect on syntactic predictions than interventions on random heads, but only in one of the two measures we propose.
Read the full abstract

Computation and Language

Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules

Sarah Pan and Ali Behrouz

Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingly large KV caches. Efficient recurrent alternatives reduce the asymptotic complexity of inference, but their sequential dependence limits token-wise parallelism during training, making them harder to scale. Further, the current paradigm of extending long context tasks creates competing notions of retaining information precisely and keeping long-context inference efficient. To address this gap, we introduce Titan-Llama, a post-training method for retrofitting attention-based language models with a hierarchical memory architecture that updates parameters at test-time. Titan-Llama applies a blockwise attention mask and preserves full-fidelity attention over recent tokens while compressing historical context into recurrent, fixed-size neural memory modules (NMMs). Our formulation allows pre-trained attention layers to be replaced without training a new language model from scratch. On Llama-3.2-1B-Instruct, Titan-Llama raises accuracy over segmented attention windows from 23.87% to 40.51% on QuALITY and from 14.50% to 40.75% on LongHealth. Inference benchmarks show more than 20% faster prefill, 37% faster decode at medium context lengths, and 24% lower steady-state decode memory usage in the evaluated configurations. Together, these results demonstrate that incorporating memory architecture mechanisms that utilize test-time training effectively modulates long-context behavior of pre-trained models, offering a practical route to adapting pre-trained transformers for efficient long-context inference. Our code is released on Github \href{https://github.com/sarahpannn/titans-pytorch/tree/main}{GitHub}
Read the full abstract

Computation and Language

DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression

Yiheng Su, Junyi Jessy Li and Matthew Lease

While work on LLM-based regression has largely focused on scalar prediction, multi-output text regression remains less explored. We present DualView, a parameter-efficient approach to leverage LLMs for multi-output text regression. \method{} first extracts broad and output-specific representations from a frozen LLM, then uses a dual-branch architecture to produce the full score vector. Across five heterogeneous regression tasks and eight LLMs (up to 122B), DualView outperforms seven supervised regression baselines while requiring 82–1842 times fewer fitted parameters than the three strongest baselines. These improvements extend across individual output dimensions and persist even with limited training data. Notably, DualView using a smaller open-weight LLM can outperform unsupervised prediction with Gemini 3.1 Pro. Controlled ablations show that broad and output-specific evidence provide complementary predictive benefits, while lightweight shared predictors achieve strong performance with fewer trainable parameters.
Read the full abstract