Computation and Language · Cross-listed from cs.MA
Population Physics, Population Problems: Safety and Emergence in LLM Societies
Adrian de Wynter
The collective behaviour of large
language model (LLM) societies is not the sum of their individual outputs. It yields statistically distinct, sometimes-unpredictable phenomena, for which the tools we use to study single
agents may not scale. Due to recent incidents involving autonomous agentic systems, however, understanding these systems is paramount. For that we introduce a framework for measuring self-organisation in LLM social systems and apply it to three such systems: a Schelling grid, a social network (Moltbook), and a Twitter-like misinformation simulation ('Rogue'). All three exhibit statistically significant self-organisation. Moreover, their relaxation dynamics vary with the environmental information available to the
agents, with open-ended systems (Moltbook, Rogue) exhibiting sharp, phase-transition-like dynamics. Further results show that population-level pathologies can emerge even when the LLMs are safety-tuned or monitored, being primarily driven by the coordinated activity of a population subset. We also show when self-organisation does not emerge under two additional scenarios (a commons dilemma, GovSim, and a LLM-as-a-judge deliberation scheme, ChatEval). We argue that measuring signatures of this kind offers a lightweight,
agent-agnostic diagnostic layer for detecting coordinated collective behaviour in deployed multi-
agent systems without relying on natural
language or model versioning.
Read the full abstract ▾
Computation and Language
In-Context Adaptation of Encoder-Decoder Models in Speech Recognition
Yen Meng, Sharon Goldwater and Hao Tang
In-context learning offers an appealing approach to adapt automatic
speech recognition (ASR) models to new speakers, accents, and domains by providing
speech-text pairs as demonstrations at inference time. Recent work shows that some LLM-based
speech models are capable of ASR in-context adaptation, when providing interleaved
speech-text demonstrations. In this work, we ask whether in-context adaptation is an inherent ability for all encoder-decoder models. We study two forms of demonstration, collated and interleaved demonstration, across six encoder-decoder models, spanning conventional cross-
attention-based and LLM-based architectures. We find that all tested models are able to perform in-context adaptation out of the box, achieving up to 30% relative improvement in the oracle experiments and up to 23% using first-pass hypotheses. Through controlled experiments on three English
datasets, we show that lexical and speaker information both contribute to successful adaptation. While interleaved demonstration is effective in certain cases, collated demonstration brings consistent adaptation across the board. Our results suggest that in-context adaptation for ASR is not unique to specific architectures, training, or demonstration approaches.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Ahmed Heakl, Sungik Choi, Moontae Lee et al. (+1 more)
Self-evolving
vision-
language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote over sampled answers or by a model judge. In a human evaluation, we find that 24% of majority-vote labels and 18% of model-judge labels produced during self-
evolution are wrong. To address this problem, we present Verifiable QA Generation for Self-Evolving Models (VQS), which changes how the model judges answers. Instead of voting on an answer, the model parses each image into a structured record, such as a scene graph, a chart table, or a diagram graph. Fixed programs then write a question from the record and compute its answer. The model still acts as a visual checker, but it only confirms the individual facts the program reads, one short claim at a time. These claim-level checks select the parser's training targets, so the parser also improves without labels. Human raters find 94% of VQS answers correct, against 76% for majority voting. Across ten
benchmarks, VQS improves Qwen3-VL by up to 3.18 points at the 2B, 4B, and 8B scales and outperforms the strongest self-evolving baseline at each. Gains keep growing over three training rounds, reaching 3.84 points at 2B. Code is released at https://github.com/ahmedheakl/VQS
Read the full abstract ▾
All authors Ahmed Heakl, Sungik Choi, Moontae Lee, Salman Khan
Computation and Language · Cross-listed from cs.LG
Rethinking Contextualization by Reinterpreting Attention Head Channels
Hakaze Cho, Haolin Yang, Zhun Sun et al. (+3 more)
Contextualization, the core operation of
language modeling, transmits information across words to build sentence-specific word representations. Prior works mainly study contextualization, focusing on individual words and
attention heads as a growing discrete dictionary, lacking a global view of their general behavior. Therefore, we propose a general principle: Globally, we find and estimate that different words carry different amounts of information, and less-informative words tend to absorb more contextual information. Specifically, these low-information words do not absorb contextual words uniformly, and finer-grained selectivity enables more precise routing to promote information transmission between matched words. Moreover, to find what mechanism causes such processing, we reinterpret
attention heads as channels gated by their singular vectors and find that: (1) these singular vectors point to the hidden states of more informative words, allowing such words to write their information to others more strongly to act as information sources, and vice versa; and (2) these singular vectors can be viewed equally as hidden state features, enabling automated interpretation of
attention heads beyond prior heuristic head discovery, also
embedding heads into a continuous space rather than treating them as discrete, independent dictionary entries.
Read the full abstract ▾
All authors Hakaze Cho, Haolin Yang, Zhun Sun, Naoya Inoue, Benjamin Heinzerling, Kentaro Inui
Computation and Language · Cross-listed from cs.AI
Laya as a Typed Probabilistic Assessor: An Independent Reproduction and a Preregistered Study of Calibration and Selective Escalation
Gowthamkumar Nandakishore
The shipped Laya Typed-Decisions checkpoint, a 421M-parameter ModernBERT-large assessor that answers typed choice/noul/score questions over workflow state, is uniformly under-confident. The signed confidence-accuracy gap is $-0.214$, every occupied reliability bin's accuracy exceeds its confidence, and that sign uniformity collapses every binned ECE variant to the same value, $0.214$. The card frames the risk as over-confidence; the measured direction is the opposite, and the direction decides which way a confidence-gated cascade fails. A single disjointly fitted temperature ($T=0.469$, sharpening) removes most of the miscalibration (held-out ECE $0.204$ to $0.037$) and outperforms the shipped per-option-count table. The frozen selection rule instead chose isotonic regression, which overfit and failed its held-out NLL contrast on both tracks, so hypothesis H2 is not supported. Re-running the released checkpoint on its full official test split reproduces the card's headline accuracy ($0.767$ vs. $0.766$). The retrospective E1 reproduction preceded the analysis freeze; E2-E8 were prospectively preregistered, and 20 of 22 executed confirmatory tests reject under Benjamini-Hochberg FDR at $q=0.05$ (two descoped). The frozen gate beats random escalation but misses its 10% accepted-set error target on both tracks, an exploratory out-of-distribution probe finds no zero-shot transfer (accuracy $0.617$), and every score measures agreement with a synthetic teacher whose self-agreement ceiling ($0.735$) the specialist exceeds. Per-decision predictions, run manifests, and the frozen preregistration are in the ancillary files. The author has no affiliation with the model's publisher, the
dataset's publisher, or TypeSafe.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning
Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song et al. (+2 more)
Large
language models are increasingly expected to support diverse chemical
reasoning capabilities within a unified model. One approach is to develop specialized capabilities separately and consolidate them through multi-teacher on-policy
distillation, but this raises two questions: how should specialization be organized, and how should specialist guidance be integrated? We introduce ChemOPD, which addresses both. We estimate task affinities from supervised fine-tuning gradients and solve a constrained mixed-integer program(MIP) to construct partially overlapping specialist groups. During
distillation, we retain a generalist teacher trained on all tasks so that specialist guidance supplements rather than replaces its supervision. Our anchor-residual objective gradually increases the routed specialist's contribution on student-generated responses. On ChemCoTBench, affinity-guided specialization produces task-dependent gains over the generalist teacher and improves several capabilities beyond semantic task grouping. Yet stronger teacher-side performance does not automatically yield stronger students: with the same specialists and routes, anchor-residual OPD improves most reported metrics over specialist-only
distillation and realizes a larger share of the available teacher gains. These results highlight specialization and capability integration as connected but distinct design problems in chemical
reasoning.
Read the full abstract ▾
All authors Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song, Xuemin Chen, Tianshu Yu
Computation and Language · Cross-listed from cs.SD
Controlling Speaking Rate in Autoregressive TTS via Activation Steering
Francesco Verdini, Antonis Asonitis, Aref Farhadipour et al. (+4 more)
Autoregressive text-to-
speech (TTS) systems synthesize natural
speech but, once trained, offer little control over speaking rate. We show that speaking rate can be steered at inference time, without retraining, by clamping a single decoder block's activation along a discovered speed axis. A decoder-block analysis recovers the rate axis, a neutral operating point, and a per-step intensity scale; at inference, the activation's projection onto this axis is set to a fixed scalar. Learning this direction from synthetically time-stretched and time-compressed
speech yields rate control that largely preserves speaker identity, generalizes across model architectures, and maintains high naturalness in objective and human evaluations. Unlike standard additive steering, which breaks at the slow extreme, clamping remains stable on all three systems tested; at moderate targets, the better rule depends on the model. Finally, we show that rate information is decodable across layers but causally steerable only within a mid-depth window, and demonstrate the effectiveness of our approach on the public Seed-TTS-Eval
benchmark.
Read the full abstract ▾
All authors Francesco Verdini, Antonis Asonitis, Aref Farhadipour, Marzieh Razavi, Pierre-Edouard Honnet, Vijeta Avijeet, Juan Pablo Zuluaga Gomez
Computation and Language
LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentation
Qing Yang, Zhenyu Mao, Zixiang Luo et al. (+5 more)
As LLM-generated text becomes increasingly human-like, accurately localizing LLM-authored spans in human-LLM co-authored documents is important for attribution and accountability in cases involving copyright infringement, fraud, and other harmful uses of AI-generated content. Sentence-level detectors provide local authorship evidence, but content variation can cause score fluctuations even among sentences from the same source, creating spurious boundaries. Recovering a coherent document partition therefore remains challenging when both the number and locations of authorship transitions are unknown. We propose Local-Evidence-Aware Change-Point Detection (LA-CPD), a structured method that transforms noisy sentence-level score sequences into coherent authorship segments. Given scores from a frozen local detector, LA-CPD combines a length-weighted within-segment residual with a windowed two-mean contrast to capture segment consistency and sustained changes around candidate cut points. Dynamic programming optimizes cut locations for each candidate count, while an AIC-style criterion selects the final partition, yielding sentence labels, authorship boundaries, and maximal LLM-authored spans. On a held-out human-LLM co-authored test set, LA-CPD outperforms WCP+AIC, increasing sentence-level accuracy from 0.747 to 0.796 while improving boundary localization and LLM-span delineation.
Read the full abstract ▾
All authors Qing Yang, Zhenyu Mao, Zixiang Luo, Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Jingwei Zhang, Jiapu Wang
Computation and Language · Cross-listed from cs.LG
Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Woongyeong Yeo, Minki Kang, Chanuk Lee et al. (+3 more)
Reinforcement learning with verifiable rewards (RLVR) enhances
reasoning in large
language models (LLMs) through outcome-level feedback, yet recent approaches to finer-grained credit assignment often require auxiliary models, additional sampling, or privileged information. Although policy
entropy provides a readily available signal, prioritizing uncertain positions under both reinforcement and penalization concentrates penalties where failed responses still retain alternatives for recovery, which can suppress opportunities for exploration. To address this, we introduce Entropic Advantage Policy Optimization (EAPO), an
entropy-guided credit assignment method that treats success and failure asymmetrically. Specifically, motivated by the observation that success under uncertainty is less repeatable while confident failures tend to recur, EAPO couples normalized policy
entropy with the sign of the response advantage to reinforce surprising success and correct repeated failure. It assigns stronger reinforcement to high-
entropy decisions in successful responses and stronger penalties to low-
entropy decisions in failed responses, while attenuating penalties at uncertain positions to preserve opportunities for recovery. By redistributing the response advantage across
tokens, EAPO derives
token-level credit directly from existing rollout signals without additional supervision. We validate EAPO on a range of
reasoning tasks across both base and
reasoning backbones, demonstrating that it achieves the best overall performance. We further show that EAPO promotes more effective exploration, broadening problem coverage and generating more diverse candidate answers.
Read the full abstract ▾
All authors Woongyeong Yeo, Minki Kang, Chanuk Lee, Sangwoo Park, Jinheon Baek, Sung Ju Hwang
Computation and Language · Cross-listed from cs.SD
Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech
Kanghwi Lee, Kyeongseok Jeong and Jeongmin Liu
Watermarking is a promising tool for establishing the provenance of AI-generated
speech. While many neural audio watermarking methods rely on a separately trained watermark generator,
token-level watermarking is a training-free alternative that operates directly during generation. Its main weakness is retokenization: decoding generated
speech to a waveform and encoding it again can change
token identities and erode the watermark. To make the watermark robust to these changes, we propose Redwing, REtokenization-Durable Watermarking IN Generation. It builds a graph from the
token substitutions observed under retokenization, whose
Laplacian yields a basis that assigns similar values to
tokens likely to substitute for one another. Over this basis,
embedding and detection functions are jointly optimized to preserve watermark signal through retokenization while limiting
embedding distortion and detector variability on unwatermarked
speech. On the Moshi full-duplex system, after eight consecutive passes of Mimi resynthesis, Redwing achieves 80.7% TPR at a calibrated 1% FPR, compared with 8.3% for KGW and at most 7.3% for WMAR. It also has the highest TPR after eight passes through three other neural codecs (77.5-93.0%), and the gains generalize to TTS models at a
speech-quality cost close to that of KGW. These results show that retokenization is not merely a source of noise: its transition structure can be exploited as a design principle for robust
token-level watermarking.
Read the full abstract ▾
Computation and Language
Positions Are Not Facts: The Mismatch Between KV Caches and Memory
Changhai Zhou, Yuhua Zhou, Shiyang Zhang et al. (+5 more)
When a fact changes, how should a
language model update the history stored in its key-value (KV) cache? Hiding the old record is cheap, but it may still contain needed details or answer questions about the past. We compare hiding whole records, hiding only replaced values, and deleting old text and recomputing the cache. In a controlled quantity task, masking makes all eight models prefer the new value more strongly, yet six lose complete answers through unit errors or failure to stop; keeping the unit preserves all current answers. Later states also retain useful information from earlier records: on multi-hop updates, rebuilding these states at unchanged positions lowers historical accuracy by 20-41 percentage points, whereas moving the existing states has little effect. Keeping object dependencies and unchanged revision passages prevents many losses. Recognition is a separate challenge. Learned readouts recover distinctions missed by fixed cache similarities on synthetic record pairs. On natural text, text-detector-selected masks show no clear advantage over random masks at the same rate in 14 same-model detector-generator comparisons. Query-dependent access can avoid some losses, with additional storage or access costs. These findings identify what must be preserved beyond the replaced value when using a KV cache as updatable
memory.
Read the full abstract ▾
All authors Changhai Zhou, Yuhua Zhou, Shiyang Zhang, Jun Gao, Zhen Li, Hua Wu, Hanchao Yu, Haifeng Wang
Computation and Language · Cross-listed from cs.SD
DuraS2ST: Chain-of-Thought and Reinforcement Learning for Duration-Aligned Speech-to-Speech Translation
Yayue Deng, Dingdong Wang, Yuxuan Hu et al. (+7 more)
Speech-to-
speech translation (S2ST) in time-sensitive applications such as
video dubbing requires not only semantic fidelity and speaker preservation, but also strict duration consistency to avoid audio-visual misalignment. However, existing S2ST systems largely generate target
speech without explicit temporal planning, making duration control an unresolved challenge. We introduce DuraS2ST, a duration-aligned
reasoning framework that enables a single
speech language model to first generate an explicit chain-of-thought (CoT) for planning target wording and phonetic length, and then synthesize the corresponding
speech tokens. To support this paradigm, we construct DuraSet-440K, a high-quality duration-aligned CoT corpus for supervised initialization. We further optimize the model with multi-modal multi-dimensional reinforcement learning, using a Duration Margin Reward to balance translation quality and duration consistency, and Modality-Aware Reward Attribution to assign rewards to appropriate
token spans. Experiments on CVSS-T show that DuraS2ST achieves a strong balance between translation quality and duration consistency, outperforming competitive open-source and commercial baselines. Project page: https://github.com/Mia11939/DuraS2ST.
Read the full abstract ▾
All authors Yayue Deng, Dingdong Wang, Yuxuan Hu, Jinyu Li, Yanqing Liu, Yuanyuan Wang, Weidong Chen, Helen M. Meng, Shujie Liu, Xixin Wu
Computation and Language
The Effects of Incremental Instruction Delivery on Language-Model Creative Writing
Anshuman Singh, Abrar Eyasir, Haseeb Yaqoob et al. (+1 more)
Large
language models are increasingly used as interactive writing tools, where users develop stories, revise ideas, and introduce new requirements across multiple turns rather than specifying a complete brief upfront. Yet most evidence on multi-turn instruction degradation comes from tasks with objectively verifiable outcomes, leaving unclear whether incremental interaction harms creative artifacts in ways that explicit requirement checks cannot capture. We study this question using 160 human-authored creative-writing tasks across six genres, presenting each intended specification either upfront or progressively over 5-9 turns to six distinct open-weight model families, yielding 960 matched pairs. Progressive delivery reduces explicit constraint adherence and produces its largest writing-quality degradation in structure/coherence. The structural gap persists among outputs with equal observed adherence, suggesting that measured requirement loss alone does not explain the observed structural difference. We define Creative Integrity as a compact measure of joint adherence and narrative structure; under incremental delivery, models retain 71.2% of FULL Creative Integrity (95% CI [68.2%, 74.3%]). A three-rater human study over 50 matched pairs independently recovers FULL advantages in structure/coherence, craft, and genre effectiveness, while automated scores remain positively associated with aggregated human ratings. These findings show that interactive creative-writing systems should be evaluated not only on whether requirements survive conversation, but also on whether evolving requirements remain coherently integrated into the final artifact. Our
dataset,
benchmarks, and source code are available at: https://github.com/solusops/SISTER-2026-Team19
Read the full abstract ▾
All authors Anshuman Singh, Abrar Eyasir, Haseeb Yaqoob, John Manavalan
Computation and Language
Yorùbá in Unicode: An Overview of a Problem
Kólá Túbòsún
There is a recurrent problem in the writing of Yorùbá on the internet and on the computer that has proven intractable over the years. The
language, along with other African
languages that depend on diacritics for disambiguation, requires a small set of precomposed characters that Unicode does not encode. This has forced writers and digital systems to rely on combining character sequences that behave inconsistently across platforms, corrupt under font substitution, and fail in search. This paper documents that failure across a range of real world contexts, from published books to web platforms to mobile keyboards, using personal and empirical evidence. It identifies Unicode's NFC normalization stability policy as the structural constraint that prevents a straightforward fix, arguing for direct intervention of the Consortium in solving the active problem, proposing a formal encoding request for the four core Yorùbá characters as the most durable path to resolution.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
BOReFT: Manifold Steering of Language Models for Black-box Optimization
Dhruv Agarwal, Rico Angell, Kavitha Srinivas et al. (+4 more)
Language models are increasingly used as proposal models for black-box search, from program optimization to molecular design. Existing approaches typically improve proposals through iterative prompting or parameter updates, offering limited control over how completely and efficiently the model's search space is explored. Continuous optimization methods, such as
Bayesian optimization, provide a principled way to search but require a suitable domain to operate over. To address this, we introduce BOReFT, which learns a compact, low-dimensional space of hidden-state interventions in a frozen
language model, and uses this space as the search domain for
Bayesian optimization with an external scoring function. Empirically, we find that the learned domain spans semantic regions and exhibits smoothness properties that support search. Theoretically, we show that semantic coverage and interpolation control the best score available in the learned space, and that decoding from this space yields a standard
stochastic-bandit observation model for adaptive search. We evaluate BOReFT on the interpretable word search task "Semantle" and on three more real-world discovery tasks in de novo molecule property optimization. Compared to strong LLM baselines, BOReFT finds in Semantle a higher number of hidden targets and, on two out of three molecular objectives, achieves higher property scores. Consequently, our method provides a principled new bridge between discrete proposal spaces of LLM-based search and continuous black-box optimization.
Read the full abstract ▾
All authors Dhruv Agarwal, Rico Angell, Kavitha Srinivas, Tahira Naseem, Horst Samulowitz, Willie Neiswanger, Andrew McCallum
Computation and Language
Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs
Shiyu Ni, Keping Bi, Jiafeng Guo et al. (+4 more)
Reliable self-assessment is essential for large
language models (LLMs), yet they often remain highly confident when their answers are wrong. We study concurrent confidence calibration, where confidence is learned alongside capability improvement rather than calibrated only after training. Reinforcement learning from verifiable rewards (RLVR) provides a natural setting for this paradigm, as it continuously produces responses paired with verifiable correctness feedback. Existing concurrent methods, however, learn both capability and confidence through reinforcement learning within shared policy parameters, potentially coupling two fundamentally different learning problems. We instead propose shared experience but separate learning: capability and confidence learn from the same trajectories, but through separate optimization mechanisms and parameters. Based on this principle, we introduce CoCal (Companion Confidence Calibration), which trains a lightweight companion from rollout hidden states and verifier-derived correctness supervision while leaving task optimization unchanged. Experiments on Qwen3-8B and Qwen3-14B show that CoCal improves confidence estimation without sacrificing task performance, outperforming both RL-based concurrent methods and matched post-hoc calibration. The learned companion further generalizes across domains and policy shifts, while the benefits of CoCal persist at both scales.
Read the full abstract ▾
All authors Shiyu Ni, Keping Bi, Jiafeng Guo, Yilong Xu, Jingtong Wu, Zengxin Han, Xueqi Cheng
Computation and Language
From Granular Revision Operations to Meaningful Revision Units: Evaluating LLMs for Revision Boundary Detection
Yu Tian, Andrew Potter, Katerina Christhilf et al. (+4 more)
Revision traces provide valuable evidence about students' writing processes, but their usefulness for learning analytics depends on how individual revisions are represented. Automated draft-comparison methods often produce granular edit operations that can fragment a single purposeful revision into multiple analytic units. This study evaluates whether LLMs can identify meaningful revision unit boundaries in structured revision operation data and whether they provide value beyond simple non-LLM baselines. Using 113 matched draft–revision pairs from undergraduate writing, expert annotation yielded 4,344 candidate boundaries. We compared zero- and few-shot GPT-5.5 and base Qwen3-32B, parameter-efficient fine-tuning of Qwen3-32B, and majority and proximity-based baselines. Despite receiving revision context and task instructions, no prompted LLM condition outperformed the proximity heuristic (macro-F1 = .825). In contrast, fine-tuned Qwen3-32B using the two context representation achieved the highest macro-F1 (.859), identifying more same-unit relationships while maintaining precision comparable to the heuristic. Deterministic post-processing substantially improved the prompted models but added little benefit to the strongest fine-tuned model. These findings suggest that LLMs can support revision boundary judgment when task-adapted, but general purpose prompting alone may not outperform transparent structural heuristics.
Read the full abstract ▾
All authors Yu Tian, Andrew Potter, Katerina Christhilf, Motahareh Darvishpour Ahandani, Jessica Early, Steve Graham, Danielle S. McNamara
Computation and Language
Understanding Confabulation and Rethinking Reconstruction in Activation Explanations
Gert Lek, Zixuan Xia, Pin-Yu Chen et al. (+1 more)
Natural
Language Autoencoders (NLAs) produce unsupervised text explanations of a model's activations: a verbalizer describes an activation and a reconstructor learns to recover it from this text. Under the established point-reconstruction NLA training recipe, explanations become more useful for predicting model behavior while also increasingly introducing unsupported details and exhibiting writing defects. To assess these changes separately, we introduce a standardized evaluation framework for unstructured NLA explanations, measuring information recoverable from explanations, contextual support for their claims, and writing quality. To address confabulation and writing defects, we move beyond predicting a single activation: explanations can distinguish distributions of possible activations even when their means and optimal point-reconstruction rewards are identical. We introduce Flow-NLA, which models the distribution of activations compatible with an explanation and trains the verbalizer using a
diffusion likelihood bound. Across Qwen, Gemma, and Apertus, this richer signal retains the utility gains of point reconstruction while curbing the growth of confabulation and writing defects, opening up a direction for improving activation-derived training to encourage more informative, supported, and readable explanations. Code and evaluation
prompts will be made publicly available upon acceptance.
Read the full abstract ▾
All authors Gert Lek, Zixuan Xia, Pin-Yu Chen, Lydia Y. Chen
Computation and Language
When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations
Máté Metzger
Classical texts aligned with their translations support machine translation,
retrieval and computational research, but evidence comparing
alignment workflows is scattered. This study compares seven systems on 452 texts in Pali, Sanskrit, Mishnaic Hebrew and Tibetan, comprising 9,833 human-aligned units: four
embedding pipelines, a direct LLM call, an autonomous
agent, and the
agent revised by an independent auditor. Generative workflows recover 93-94% of reference correspondences, against at most 77% for
embeddings. A ceiling analysis shows that sentence boundaries make some references unrepresentable by the
embedding pipelines. Reference recovery is similar across generative workflows: the
agent's advantage is 0.5 percentage points (95% CI -0.02 to 1.17), and auditing adds no established benefit.
Agents nevertheless produce structurally valid output for all 452 texts, against 437 for direct calls. A blinded three-LLM panel assesses every generative mismatch against the source and human reference. Most mismatches are labelled defensible editorial variation; consensus major-error labels cover only 0.06-0.14% of units. The panel labels significantly fewer residual defects for
agents than direct calls (0.7% versus 1.4%), suggesting that reference recovery alone understates
alignment quality. On ten long Pali discourses taken as published online,
agents and audited
agents raise recovery from the direct call's 71% to 84% and 92%. Identical reference-located chunks bring all three to 93%.
Agents thus improve structural reliability and reduce judged defects on short passages, while their large recovery advantage on long documents disappears after chunking. In this setting, independent auditing offers little measurable additional benefit on prepared passages.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Auditing Agent Actions through Query-Conditioned Attribution
Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo et al. (+1 more)
LLM
agents increasingly take consequential actions through interactions with users, policies, and external tools. Auditing these
agents requires automated attribution of realized actions to their historical basis. However, existing attribution formulations do not provide question-specific traces for diverse auditing objectives. Additionally, when access to the acting model is limited (e.g., in API-only deployments), applicable methods commonly rely on costly input perturbations or external LLM analysis of complete trajectories. We therefore formulate query-conditioned
agent action attribution, a new task that takes a natural-
language auditing query as input and recovers the source and ordered intermediate evidence for the query-specified aspect of an action. We instantiate this task with $A^3Bench$, a
benchmark comprising 1,396 auditing queries across policy basis, parameter provenance, failure propagation, and unsafe-behavior tracing. To enable efficient, query-specific attribution, we use small open-weight models as attribution proposers that combine query-conditioned gradient saliency with query-semantic relevance to rank history units. Our proposer consistently achieves stronger source and evidence rankings at lower inference cost than open-weight baselines, improving source MRR by up to 40.9% and evidence MAP by 42.1% with only two forward passes and one backward pass. Controlled evaluations confirm that our proposer improves attribution specificity by adapting its rankings to fine-grained changes in the auditing query. Building on a proposer ensemble, our end-to-end system surpasses the strongest frontier-model baseline in source accuracy (64.5% vs.\ 60.4%) while reducing empirical deployment latency by 29.9% relative to the fastest frontier API baseline. Code and data will be released after the initial review period following final validation and cleanup.
Read the full abstract ▾
All authors Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo, Dong Wang
Computation and Language
Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis
Adi Shnaidman
Grounded
language models are usually evaluated by adding relevant context, but multiturn dialogue also contains unsupported user claims that may contaminate later factual answers. We study post-pressure recoverability: whether a model returns to clean-context behavior after a user repeatedly advocates a wrong answer and then withdraws that pressure. We introduce a recovery-after-pressure protocol for multiple-choice factual dialogue and measure sycophancy hysteresis, the residual probability assigned to the user-advocated wrong answer relative to a clean-context counterfactual. Across seven instruction-tuned open-weight models and two factual
benchmarks, ordinary reset often reduces but does not erase pressure-induced bias. History preserving repairs such as user retraction, system reset, and self-verification recover only 2-3/14 model-
dataset pairs under the strict clean-restoration diagnostic, whereas operations that change the effective context are substantially more reliable; the two conditions that remove the pressure-bearing history entirely, fresh-context deletion and context truncation, recover 14/14. In an oracle trusted-evidence condition across fourteen model-
dataset pairs, preserving the pressure-bearing history while adding
benchmark-derived trusted evidence increases accuracy from 0.368 to 0.929, while wrong-answer following falls from 41.2% to 4.3%. Controls show that the effect is not explained by dialogue length, repeated confidence, plausible distractors, mere false-answer mention, or option-label inertia. These results suggest that faithful grounded dialogue requires evaluating which prior context should be treated as evidence and which should be removed or quarantined before answering.
Read the full abstract ▾
Computation and Language
Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL
Corentin Royer, Robin Oester, Yotam Perlitz et al. (+3 more)
Text-to-SQL systems are typically trained and evaluated on a single dialect (SQLite), yet production deployments span PostgreSQL, MySQL, ClickHouse, and beyond. We show that this single-dialect assumption leads to a substantial drop in cross-dialect accuracy for every model we tested. The drop persists across scale, architecture, and even purpose-built text-to-SQL systems. We argue that the fix is to change the generation target: instead of asking an LLM to emit dialect-specific SQL, we have it emit a dialect-agnostic relational
algebra query plan, which a deterministic compiler then renders into SQL for any supported backend. Across thirteen models from 3B to frontier scale, this restores cross-dialect portability nearly uniformly, at a small cost in peak accuracy on the model's home dialect for capable prompted models and none once fine-tuned on plans; under matched fine-tuning, plan supervision yields a stronger model than SQL supervision. We also introduce MetricName, a question-aware result-set comparator needed to evaluate fairly across dialects, where existing metrics confound semantic errors with benign cross-dialect variation. More broadly, the result is a reminder that a generation target chosen for execution is not necessarily the one that maximizes generation quality.
Read the full abstract ▾
All authors Corentin Royer, Robin Oester, Yotam Perlitz, Yannick Metz, Andrea Giovannini, Mennatallah El-Assady
Computation and Language
One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation
Nafis Irtiza Tripto, Delvin Ce Zhang, Mahjabin Nahar et al. (+1 more)
Human communication on the internet is shaped by diverse perspectives, most visibly expressed in online comment spaces. As large
language model (LLM)based AI
agents begin to inhabit these spaces, a key question arises: whether synthetic comment threads can capture the diversity inherent in human discourse. This concern is increasingly important, as the growing presence of homogenized AI-generated content risks reducing diversity over time, potentially leading to model collapse and degrading the richness of digital communication. Inspired by the plurality of human crowds and the aspect-driven nature of discourse, we hypothesize that comment diversity is better approximated by combining multiple LLMs with aspect-conditioned generation. We formalize and evaluate this approach using models from different providers and introduce a framework that characterizes diversity across semantic, linguistic, and socio-pragmatic features along three axes: dispersion, coverage, and
alignment. Using this framework, we conduct a large-scale study on over 2 million YouTube comments across multiple domains. Our results reveal that multi-LLM and aspect-conditioned generation better align with human comment distributions and such data remains viable under pretraining style curation and is effective for downstream tasks. Yet, human diversity remains unmatched. Overall, our findings provide a practical foundation for generating more diverse and socially grounded discourse in AI-mediated environments.
Read the full abstract ▾
All authors Nafis Irtiza Tripto, Delvin Ce Zhang, Mahjabin Nahar, Dongwon Lee
Computation and Language · Cross-listed from cs.AI
Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+5 more)
Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates discrete directional admission from continuous magnitude control. An observation-only accept-appeal-abstain policy uses a finite secondary-verification budget; its action trace is frozen before clean labels are joined. Simultaneous finite-sample bounds then certify selected harmful risk, coverage, and verifier-call rate over a predeclared policy family. Conditional Hoeffding-Azuma bounds account for the dependence induced by shared budgets, and rollout or verifier changes initiate a new certification stage. After admission, a bounded trust-clip-KL actuator controls magnitude. We evaluate two models on two
reasoning benchmarks against static RLVR, matched-random selection, confidence thresholding, noise correction, and verifier augmentation. On Qwen3.5-0.8B and GSM8K at target risk $\rho=0.08$, RC-VAPO achieves 74.1% accuracy, selected harmful risk 0.0697, coverage 0.4125, and relative verifier cost $1.16\times$. At matched coverage and update magnitude, its selected-risk difference from matched random is -0.0260 with paired 95% interval $[-0.0364,-0.0157]$. Across asymmetric, confidence-dependent, and correlated-verifier noise, the certificate is satisfied on 57 of 60 independent runs. These comparisons isolate informative directional selection from proposal suppression, update shrinkage, and additional verifier computation.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Rui Chen, Daren Zha, Jun Xiao
Computation and Language
Tsubame: Tree Replay for Diffusion-Based Speculative Decoding
Yepeng Weng, Qiao Hu and Takehisa Yairi
Context-aware dynamic trees allocate the speculative decoding budget according to draft path probabilities, adapting their depth and branching to the current context. Under
stochastic decoding, however, we find that this structural advantage does not always compensate for the acceptance gains of random sampling paired with advanced verification, and such dynamic trees can fall behind sampled chains in some settings. These trees grow their
topology from the candidates themselves, so the
tokens submitted for verification are typically the deterministic high-score
tokens selected during construction. This coupling is not inherent: once the
topology is fixed, its nodes can be repopulated by sampling, allowing dynamic trees to retain their structural advantage while also benefiting from random sampling and advanced verification.
Diffusion-based drafters make this practical, as their parallel outputs or lightweight conditional corrections allow candidates to be regenerated cheaply after the complete
topology is known. We introduce Tsubame, a two-pass tree speculative decoding framework for
diffusion-based drafters. The first pass plans and freezes a context-aware
topology using draft path scores; the second replays the fixed
topology, sampling the
tokens that populate its nodes to form the candidate tree for verification. We prove that Tsubame is lossless under compatible sampling and verification strategies. Experiments across three
diffusion-based drafters, six
datasets, and multiple candidate budgets show that Tsubame improves acceptance length and throughput over deterministic trees, including settings where it reverses their disadvantage against sampled chains.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Probe to Act: Elevating Browser-Use Agent via Active Visual Probing
Keliang Li, Heng Wang, Chen Hu et al. (+3 more)
Browser-use
agents require seamless
alignment between structured web metadata and visual information, while preserving relevant context across long interactions. Existing interfaces often rely on either screenshot-level action prediction or static Set-of-Marks overlays, leaving the model to resolve dense DOM-pixel
alignment before every operation. We introduce Probe to Act (P2A), an active probing framework for the browser-
agent loop that moves this
alignment into decision time. P2A addresses an asymmetric bridge between symbolic DOM hypotheses and screenshot layout by rendering on-demand symbolic DOM structure back into pixels. Before committing a state-changing browser operation, the
agent can issue lightweight probes to translate DOM handles into pixel evidence, map screen regions back to DOM candidates, register visual-only targets, and commit verified notes. These interleaved processes naturally produce evidence-based
memory: only probed, acted-on, or explicitly committed observations are kept across steps, preserving only decision-critical evidence in long-horizon contexts. P2A can be used as a prompting strategy for proprietary models under the standard DOM+SoM interface, and can be distilled into open-weight models through cold-start synthesis and self-bootstrapped SFT. Across three browser-use
benchmarks, P2A shows clear gains on task success rate for both proprietary and fine-tuned models; on VisualWebArena, for example, it improves Gemini-3-Pro from 54.1% to 61.2% and Qwen3-VL-8B from 24.6% to 32.9%, while matching the costly full-observation history ($\sim$3$\times$) at only $\sim$1.2$\times$ the peak retained input context of action-only history.
Read the full abstract ▾
All authors Keliang Li, Heng Wang, Chen Hu, Daxin Jiang, Hong Chang, Shiguang Shan
Computation and Language
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Haoyi Wu, Yang Xiao, Yusong Sun et al. (+4 more)
Real-world tasks often require large
language models (LLMs) to learn from complex task-specific context rather than pretrained parametric knowledge. This capability remains a weakness of LLMs, while human annotation for such task contexts is expensive and difficult to scale. Public high-quality documents are an abundant alternative, but much of the public web has already been consumed during pretraining: training on such documents naively would reward memorization rather than context learning. In this work, we attempt to make use of high-quality public documents with small perturbations and empirically find that LLMs can successfully generate context-dependent
reasoning traces and answers, which are then used to train a student model. Specifically, we construct a synthesis pipeline that (i) rewrites source documents to reduce memorization risk, (ii) generates questions and rubrics that require
reasoning over the document, (iii) answers the questions with the document as context, and (iv) admits only samples that genuinely depend on the document. Without any human annotators, our pipeline generates about 10k samples from 3.5k documents, and the resulting student model substantially improves the performance on CL-bench. SFT raises a Qwen3.6-35B-A3B student from 13.7% to 22.8%, and a subsequent rubric-reward RL stage reaches 24.6%, on CL-bench comparable with a frontier model of over a trillion parameters, Qwen3.8-2.4T (23.9%). We also observe a broad transfer of improvements to long-context understanding, instruction following, and
reasoning, while code generation and knowledge remain mostly flat. We hope this work provides a reproducible and scalable way to improve the ability of LLMs to learn from context, and to facilitate further research on context-grounded
reasoning.
Read the full abstract ▾
All authors Haoyi Wu, Yang Xiao, Yusong Sun, Wenyang Hui, Zhaokai Luo, Chengyue Jiang, Mu Chuan
Computation and Language · Cross-listed from cs.LG
Quantifying Behavioral Tails in Black-Box Language Models
Elsayed Eshra, Ali Al-Lawati, Dongwon Lee et al. (+1 more)
We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large
language models (LLMs). A key challenge for probability estimation is defining a tractable distribution over the input space. To accomplish that, RareTrap uses a surrogate LLM and constructs a geometry-aware mapping from a lower-dimensional latent reference space into its
token-
embedding space to induce an explicit and reproducible distribution over input
prompts. A response-level performance function is utilized on the response to quantify behavior severity. This enables sequential rare event simulation that concentrates evaluations on progressively more severe behaviors while preserving probability under the induced
prompt distribution, which would otherwise be prohibitive to measure. Across 10 open-weight and two frontier models (GPT-5.4 and Claude Sonnet 4.6), we find that RareTrap successfully induces severe resource consumption behaviors and computes their probability with as few as 200 evaluations. RareTrap provides model developers a principled approach for evaluating
language models under a common distribution, and prioritizing
alignment effort to improve safety and mitigate risks.
Read the full abstract ▾
All authors Elsayed Eshra, Ali Al-Lawati, Dongwon Lee, Suhang Wang
Computation and Language
Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
Gert Lek, Abele Malan, Chaoyi Zhu et al. (+3 more)
Guard models are the last line of defense between a
language model and a harmful output, yet their training objective is surprisingly narrow. Existing guards learn to predict a single verdict
token from a conversational context, concentrating supervision on a single target. The consequences are structural: models latch onto shortcut features, are overconfident, and remain sensitive to where safety evidence appears in the sequence rather than its role in the full context. We propose a different framing. Rather than predicting a label from text, our LLaDA-Guard asks which label better explains the text: scoring the
prompt or response under each label hypothesis and classifying based on their difference. This shifts supervision to every
token in the moderated region, forcing the model to account for full content rather than its most discriminative fragments. We instantiate this idea with a masked
diffusion language model, fine-tuning LLaDA-8B-Instruct with a class-conditional reconstruction objective using LoRA and requiring no architectural changes beyond the base model. LLaDA-Guard leads on average rank against discriminative baselines trained on stronger backbones across seven held-out safety
benchmarks, while exhibiting substantially better confidence calibration (ECE 0.0875 vs. 0.1384 for Qwen3Guard), less over-defense on benign
prompts with unsafe-looking cues, and less
prompt leakage when moderating responses. Its generative nature further enables
token-level risk localization as a natural byproduct, yielding a pipeline for rewriting unsafe
prompts into safe equivalents without additional training and achieving a 60.7% average conversion-to-safe rate.
Read the full abstract ▾
All authors Gert Lek, Abele Malan, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Chen
Computation and Language · Cross-listed from cs.AI
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments
Shengbin Yue, Hongru Wang, Siyuan Wang et al. (+3 more)
Language model
agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods face a performance-efficiency tradeoff: they either rigidly decouple exploration and execution or interleave them without coordination. We argue that the key lies not in whether to decouple or interleave them, but in how to coordinate them across granularities. We introduce ParaAct, a structured parallel-action loop that combines phase-level Exploration $\rightleftharpoons$ Execution with action-level parallelism. To learn this loop, ParaAgent combines multi-
agent cold-start demonstrations with reinforcement learning under multi-level advantage decoupling, making planning structure explicit and supervising it with step-, phase-, and trajectory-level rewards. Learning is supported by our ToolEnv, a scalable simulator grounded in 50,011 realistic tool interfaces. On two open-world tool
benchmarks, ParaAgent-4B achieves the best average success among all baselines, including GPT-4.1 systems, with the largest gains on multi-tool tasks. Behavioral analyses show that these gains stem from this action organization, highlighting its importance for capable and efficient open-world
agents.
Read the full abstract ▾
All authors Shengbin Yue, Hongru Wang, Siyuan Wang, Xiaoxin Chen, Wei Chen, Zhongyu Wei