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

Tuesday 11 August

Computation and Language

X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction

Kaiqi Fu, Rime Wen, Altman Lin et al. (+4 more)

Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchannels that should be ignored, and the completion of an utterance. Prior modular approaches typically optimize turn state prediction at the utterance or fixed-chunk level, creating a mismatch with the continuous turn state estimate, and often depend on an auxiliary ASR model, which limits responsiveness and increases overall system complexity. Therefore, we present X2-Turn, a frame-synchronous turn state prediction method via delayed-stream modeling. Specifically, building on the pretrained Voxtral Realtime model, we introduce a frame-synchronous turn state head that operates in parallel with the ASR head on shared streaming representations, jointly predicting ASR tokens and fine-grained turn states at the frame level. Experiments on bilingual EasyTurn and Full-Duplex-Bench demonstrate that the proposed method achieves an effective trade-off between turn state accuracy and decision latency.
Read the full abstract

All authors Kaiqi Fu, Rime Wen, Altman Lin, Shawn Qin, Roy Gan, Hao Wang, Qian Wang

Computation and Language

VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?

Xiaohongshu Dots Studio and Evolvent AI

Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments. Everyday life assistance is different. A task runs for weeks rather than minutes. The world keeps changing while the agent is not being prompted. Many constraints are never stated outright. An agent that merely answers the request in front of it will fail at such a task. What is needed instead is an agent that stays proactive and consistent. It decides on its own when to act, when to ask, and when to stay silent. It notices changes that nobody announced. It keeps one plan coherent from the first day to the last. No current benchmark measures this. We introduce VibeLifeBench, a benchmark of 200 long-horizon tasks across ten everyday-life domains. Each task is a scripted multi-week timeline in a simulated world of 22 mock services. The world advances on its own clock, and many of its changes are silent, so only an agent that re-inspects the world discovers them. Every task is graded by fine-grained, weighted checks that read only what the agent actually left behind, covering the end state, the timeliness of its actions, and whether it upheld the implicit constraints. We evaluate seven frontier models. All of them score low, which shows how far current agents are from assisting with real life. We will open-source all tasks, environments, and the evaluation framework.
Read the full abstract

Computation and Language

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

Chris Han, Pengzhi Gao, Pei Fu et al. (+1 more)

We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models, we apply Group Relative Policy Optimization (GRPO) with a reward that averages two reference-free quality estimation models and is gated by language identification. We then linearly interpolate the supervised fine-tuning (SFT) and reinforcement learning (RL) model checkpoints to obtain MiLMMT-46-v1.0. Across 46 languages, the resulting models consistently improve translation quality over their SFT counterparts, outperform strong recent open baselines, including Seed-X, HY-MT2, and TranslateGemma, and achieve leading reference-free scores against evaluated proprietary systems such as Google Translate, Gemini 3 Pro, and GPT-5. We further investigate on-policy distillation (OPD) and find that it reaches, but does not surpass, the quality frontier achieved by RL with checkpoint interpolation. We release the models and code to facilitate future research.
Read the full abstract

All authors Chris Han, Pengzhi Gao, Pei Fu, Jian Luan

Computation and Language

Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse

Zhenyan Zheng, Yunyao Zhang, Junxi Sheng et al. (+2 more)

Emotion understanding in discourse requires reasoning beyond surface sentiment because speakers often convey affect through indirect, implicit, polite, ironic, or deliberately mismatched expressions. Existing emotion benchmarks mainly annotate surface polarity or final emotion categories, while lacking a structured account of how explicit expression, implicit affect, pragmatic intent, and fine grained emotion interact. This limitation makes current evaluations insensitive to cases where affective meaning is concealed, weakened, inverted, or pragmatically reshaped, thereby obscuring model failures in deeper emotion understanding. To address this gap, we introduce CUE Bench, a Chinese Unsaid Emotion benchmark that centers on Affective Stance and covers diverse communicative scenarios. CUE Bench constructs nine human interpretable affective stances from explicit implicit polarity interaction and further provides intent and fine grained emotion annotations for structured affective inference. Experiments show that incorporating Affective Stance improves fine grained emotion recognition by 3.1 percentage points and pragmatic intent detection by 8.1 percentage points over strong baselines.
Read the full abstract

All authors Zhenyan Zheng, Yunyao Zhang, Junxi Sheng, Junqing Yu, Zikai Song

Computation and Language

Assessing Reliability of BERT-Based Models on Question Answering Tasks

Pooja Yadav, Priyanka Harjule, Basant Agarwal et al. (+1 more)

Reliability estimation of large language models is in many cases as crucial as their accuracy, as reliable models are more trustworthy, robust, and suitable for practical applications. Recent advancements in natural language processing (NLP), particularly those based on transformer architectures, have significantly accelerated progress across various NLP tasks. This study focuses on the reliability of transformer-based question answering (QA) models, specifically BERT models and its variants (RoBERTa, ALBERT, DistilBERT). These encoder-only pretrained transformers have demonstrated remarkable accuracy in QA tasks that can be treated as classification tasks. However, their reliability remains underexplored. This study evaluates the reliability of four BERT-based models by assessing response stability under two conditions: (1) internal model variations induced via Monte Carlo Dropout (MCD) and (2) input perturbations through paraphrasing. Using the SQuAD and QuAC datasets, we investigate how dropout rates affect prediction consistency and whether lexical changes impact answer stability. Our findings reveal that RoBERTa maintains higher reliability, whereas AlBERT and DistilBERT exhibit significant inconsistencies. Statistical analyses confirm that enabling MCD during prediction does not disrupt inference dynamics, validating its effectiveness as a reliability metric. These findings underscore the importance of evaluating both accuracy and stability in QA models to ensure stability in real-world applications.
Read the full abstract

All authors Pooja Yadav, Priyanka Harjule, Basant Agarwal, Marko Robnik Šikonja

Computation and Language

Mitigating Context Interference for Reliable and Efficient Search Agents

Boyang Xue, Bin Wu, Shuofei Qiao et al. (+8 more)

Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would inevitably introduce irrelevant information that distracts LLMs, referring to context interference, potentially hindering the reliability and efficiency of search agents. Therefore, we conduct a systematic study on context interference in multi-turn search agents, focusing on investigating i) which parts of the context of search agents will contribute to the context interference, ii) how to refine the contexts of search agents to mitigate the interference, and iii) can incorporating context refinement into search agent training yield further improvements. We reveal that interference primarily arises from the latest retrieved documents. Based on the explored findings, we then introduce a distill-based context refiner to dynamically mitigate context interference for multi-turn search agents. Finally, we validate that incorporating context refinement into RL training pipelines of search agents can significantly enhance both reliability and efficiency. This study highlights the importance of mitigating context interference of search agents, inspiring a novel paradigm of “refine context and then generate” for AI agents.
Read the full abstract

All authors Boyang Xue, Bin Wu, Shuofei Qiao, Sheng Wang, Rui Wang, Yiming Du, Hongru Wang, Jeff Z. Pan, Emine Yilmaz, Kam-Fai Wong, Aldo Lipani

Computation and Language · Cross-listed from stat.ME

When Is a General Factor Distinguishable? Non-Proportionality, Stable Structure, and the Bifactor Decision

Jinsong Chen

Whether an added general dimension is necessary beyond correlated first-order factors is a property of population covariance, not an estimator. A bifactor structure is covariance-equivalent to correlated factors when general and group loadings are proportional within every cluster. When every cluster violates proportionality, at least three indicators per cluster and mild conditions rule out exact reproduction by a K-factor model with diagonal uniquenesses. Mixed configurations remain only partly characterized, motivating graded distinguishability. We develop a two-step procedure that delivers a stable first-order structure only when it persists across direct wider-count comparisons, then compares oblique and bifactor representations conditionally on delivery. A preliminary simulation study provides tentative design evidence. A major study develops three non-nested persistence profiles, designates .80/r2 as the practical default, and evaluates the frozen family on held-out replications from the same generators. Within the studied scenarios, anchor-only persistence outperforms anchor-zero, minimum congruence modestly outperforms maximum RMSD, and depth four adds no precision at the fixed .70 cutoff. Held-out results also expose stable-yet-wrong delivery under a weak core and show that the conditional comparison is highly accurate after correct recovery. Four empirical applications illustrate agreement, adjacent-count uncertainty, and non-delivery. Persistence, not count alone, carries the structural decision.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence

Haoyu Zhang, Zhipeng Li, Xiaoying Tang et al. (+2 more)

Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, but a spoken answer still leaves the agent visually absent. We introduce Ex-Omni-2D, a framework that answers a multimodal query with coordinated text, personalized speech, and reference-conditioned video. The dialogue model first writes a structured Visual Thought Plan (VTP) for scene, emotion, and motion, then generates the response text and multi-codebook speech units. These speech units are decoded into audio and aligned with video frames, giving the speech and avatar modules a common timing signal while allowing them to learn from different data sources. The video module is trained as a full-sequence Teacher conditioned on reference appearance, VTP semantics, and frame-aligned speech units. We further explore to distill it into a few-step block-causal Streaming Student; its Prefix Streaming mechanism carries the previous clean latent into the next chunk and is analyzed as a partial mitigation for late-chunk subject drift. At $400\times720$/$720\times400$, the four-step four-GPU Student provides incremental output with lower startup latency than the full-sequence Teacher.
Read the full abstract

All authors Haoyu Zhang, Zhipeng Li, Xiaoying Tang, Tianshu Yu, Yiwen Guo

Computation and Language · Cross-listed from cs.SD

DuplexWorld: Can voice agents help you get through the day?

Aryan Vijay Bhosale, Harshit Rajgarhia, Akhil Pothanapalli et al. (+3 more)

Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing to the ease of the conversational modality over text. However, existing benchmarks fail to holistically evaluate voice agents along axes that really matter and are shaped as tests of agentic tool calling against a database. We believe they fail to adequately account for the diversity of conversational dialogue that mundane activities introduce and further, never test how faithfully an agent can assist on tasks that move beyond database manipulation. To tackle this DuplexWorld introduces six worlds where voice agents are especially useful: banking, insurance, travel, healthcare and logistics, and Pathfinding. Agents are evaluated on eleven different types of conversations across 156 scenarios (350+ hours of conversation), each testing conversational and analytical capability to varying degrees. Through extensive evaluation comprising agentic, conversational and speech-naturalness metrics, we show that even the best voice agents leave substantial room for improvement on all 3 axes (Pass@1: 0.490, turn-taking: 0.653, DNSMOS: 3.378). We perform extensive analysis on agentic v conversational performance, world- and conversation type-wise performance, failure modes exploring the explore v exploit lens for Pathfinding conversations and voice agent reliability over all six worlds.
Read the full abstract

All authors Aryan Vijay Bhosale, Harshit Rajgarhia, Akhil Pothanapalli, Asif Shaik, Abhishek Mukherji, Dinesh Manocha

Computation and Language

Most biomedical publications show signs of LLM-assisted writing

Lena Holzwarth, Rita González-Márquez and Dmitry Kobak

Over the past several years, LLM-powered chatbots and agents have become widely used as a tool for academic writing. LLM-assisted writing can be valuable by removing language barriers but at the same time causes concerns about misconduct and fraud. To inform policy decisions, it is necessary to monitor the prevalence of LLM-altered texts in scholarly publications. Despite some recent progress in this direction, no existing method can produce reliable estimates. Here we suggest and validate a new unbiased approach to estimate LLM usage in a corpus of texts based on changing word frequencies. We apply our method to the full texts of open-access biomedical papers from Pubmed Central, and show that by the end of 2025, 89% of papers show excess of LLM-associated vocabulary. We also find that LLMs are twice as likely to be used when writing a paragraph in the Discussion section (68%) compared to a paragraph in the Methods section (32%), but even inside the Methods section, the overall prevalence of LLM usage is over 50%. We believe that our estimates are crucial to shape future guidelines and policies.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control

Haoze Liu, Run Liu, Haiying Xu et al. (+6 more)

Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making. Existing LLM personality studies largely rely on self-report questionnaires administered in first-person settings, making the resulting profiles sensitive to surface elicitation choices and poorly grounded in concrete model behavior. In this work, we introduce a situated behavioral-data (B-data) framework for studying and controlling LLM behavioral personality. We construct 3,200 contrastive behavioral scenarios spanning 20 behavioral patterns and four prompt registers, grounded in validated psychometric facets such as BFI-2, DOSPERT, and HEXACO. Using this framework, we find that LLMs exhibit stable and model-specific behavioral profiles, while also revealing register-dependent shifts across first-person decisions, advice-giving, and task execution. We then show that these behavioral patterns can be controlled through Behavioral Mode Axes (BMAs), activation-space directions derived from contrastive behavioral traces. Compared with response-derived BMAs, which are more prone to trait drift, thought-derived BMAs more faithfully capture the intended behavioral mechanism and provide cleaner control over situated behavioral styles. Our results suggest that LLM personality-like tendencies are better understood not as abstract self-report traits, but as measurable and controllable behavioral modes grounded in concrete interaction contexts. Our code and data are available at https://github.com/lhz191/LLM-Behavioral-Personality.
Read the full abstract

All authors Haoze Liu, Run Liu, Haiying Xu, Jiahui Han, Siyuan Fang, Siyu Yan, Huiqi Deng, Guanchu Wang, Na Zou

Computation and Language

EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection

Hongrui Bao, Hangyu Rong, Zhuoshang Wang et al. (+2 more)

The rapid development of large language models (LLMs) has increased the need for reliable detection of LLM-generated text, especially in realistic Chinese scenarios involving human-written text (HWT), LLM-generated text (LGT), and LLM-refined text (HLT). This paper presents EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for NLPCC 2026 Shared Task 6. The system integrates edit-extent regression, zero-shot likelihood-contrast signals, lexical statistics, and conservative text rules. With calibrated decision boundaries and conflict-aware integration, our system improves robustness under strong out-of-distribution shifts, achieving a macro-F1 score of 0.8888 and ranking first in the official evaluation. Our code is available at https://github.com/bbbbhrrrr/evildetect.
Read the full abstract

All authors Hongrui Bao, Hangyu Rong, Zhuoshang Wang, Yubing Ren, Yanan Cao

Computation and Language · Cross-listed from cs.LG

Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization

Tal Oved, Roi Pony, Oshri Naparstek et al. (+1 more)

Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, so the evaluator's price tier dictates total search cost. We restructure that search by decoupling the three roles an LLM plays, running the high-volume answering role on the cheapest tier, reserving a strong model for the rare reflection/variation operator, then exploiting upward cross-tier transfer to deploy the cheaply evolved prompt on a stronger target. We contribute a cost-controlled characterization of when cheap-tier search substitutes for target-tier search, and where it fails. Across four tasks (HotpotQA, IFBench, LiveBench-Math, HoVer) and eleven models in four model families, the resulting prompt matches or exceeds same-tier optimization while placing over 96% of search tokens on the cheapest tier, at 5.6-14x lower search cost, rising to 25-54x where reasoning tiers emit long chains of thought on every fitness call.
Read the full abstract

All authors Tal Oved, Roi Pony, Oshri Naparstek, Udi barzelay

Computation and Language

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Junjie Ye, Zhuohui Sheng, Shaofan Liu et al. (+12 more)

Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. To address this gap, we introduce SPIEval, a human-curated benchmark grounded in five cognitive capabilities (i.e., reasoning, disambiguation, integration, preference inference, and multi-intent decomposition). SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools. Analysis shows that the benchmark exhibits diverse scenarios, challenging tasks, scattered information, controllable environments, and verifiable outcomes. We evaluate nine representative LLMs and find substantial room for improvement. The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%. Further analysis reveals that 79% of failures stem from inaccurate information localization, as LLMs often commit to plausible but incorrect information instead of continuing retrieval for verification. We also find that fewer than 2% of retrieval actions employ advanced search methods and observe substantial variation in search efficiency across models. These findings expose fundamental limitations of current LLM-based mobile assistants and motivate future research in this direction. Data and code are available at https://huggingface.co/datasets/Junjie-Ye/SPIEval.
Read the full abstract

All authors Junjie Ye, Zhuohui Sheng, Shaofan Liu, Yulun Zhu, Wenjie Fu, Dingwei Zhu, Ming Zhang, Yujiong Shen, Weichao Wang, Xin Zhao, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang, Pluto Zhou

Computation and Language

Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?

Qingjie Zhang, Xingzhang Ren, Zixuan Chen et al. (+6 more)

Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific token groups from released tokenizer vocabularies; in contrast, we estimate corpus ratios for arbitrary target tokens. We first show that BPE tokenizers trained on different corpora share stable token ID–ratio distributions, motivating distribution transfer from known corpora to a target tokenizer trained on hidden corpora. We then propose Quantile-Guided Density Estimation (QGDE), which approximates this distribution with multiple quantile trends and uses local density weighting to produce token-level estimates. In controlled settings and a realistic setting using the released SmolLM tokenizer, QGDE achieves mean relative errors as low as 3.00% for token-level estimation and 3.08% after aggregation into category-level mixtures. These results suggest that released tokenizer vocabularies provide a useful signal for fine-grained corpus estimation beyond coarse composition inference.
Read the full abstract

All authors Qingjie Zhang, Xingzhang Ren, Zixuan Chen, Jinfeng Li, YueFeng Chen, Yitong Yang, Hui Xue, Dayiheng Liu, Han Qiu

Computation and Language · Cross-listed from cs.HC

The Signal Rail: A Deterministic Motion Grammar for Communicating Conversational Agent State in Terminal Interfaces

Matteo Grella

Terminal interfaces to conversational agents report rich internal state (listening, thinking, executing tools, awaiting input, failing) almost entirely through text, while the motion channel beside it, the one peripheral vision monitors without reading, carries a single bit: alive. We present the Signal Rail, a one-row terminal status instrument that gives that channel a grammar. Four ideas govern it: spatial semantics (input, processing, and output zones, with direction as meaning), a motion grammar (one kinetic rule per state, never color alone), determinism (frames as a pure function of explicit inputs, golden-frame testable), and honesty (no invented progress or activity). We contribute a 45-section normative specification and a reference implementation inside a working full-duplex local voice agent driven by real signals.
Read the full abstract

Computation and Language

Leveraging Human Reading Behavior for Keyphrase Extraction: A Webcam-based Eye-tracking Corpus

Chengzhi Zhang, Xinyi Yan and Wenqi Yu

Purpose: Keyphrases are statistically and semantically important textual units that can also attract readers' attention during comprehension. However, existing keyphrase extraction (KPE) studies mainly focus on improving textual representation while largely overlooking human reading behavior. This study examines whether lightweight webcam-based eye-tracking features can improve KPE from Chinese academic abstracts in Library and Information Science (LIS). Methodology: To address the limited availability of eye-tracking data for Chinese academic reading, we developed a lightweight webcam-based data collection platform using the open-source SearchGazer library and constructed the Chinese LIS Eye-Tracking Corpus (CLIS-ET). Three character-level eye-tracking features, first fixation duration (FFD), fixation number (FN), and total fixation duration (TFD), were incorporated into KPE models to evaluate their effects on extraction performance. Findings: Eye-tracking features consistently improved KPE performance. The combination of FN and TFD achieved the best results on the Att-BiLSTM+CRF model, indicating that readers' fixation behavior provides useful signals for identifying keyphrases in academic abstracts. Originality/value: This study introduces a cost-effective webcam-based eye-tracking approach for KPE and presents CLIS-ET, a Chinese academic eye-tracking corpus containing FFD, FN, and TFD features. The results demonstrate the value of incorporating human reading behavior into keyphrase extraction. Dataset and code: https://github.com/yan-xinyi/ET_AKE and https://github.com/yan-xinyi/Reading_ET_System.
Read the full abstract

Computation and Language · Cross-listed from cs.IR

ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering

Akrin Zheng, Alexander Wu and Alaia Liu

Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are work by-products in which required organizational relations remain implicit across heterogeneous sources. Existing benchmarks provide realistic multi-source evidence, but often materialize a predefined answer path and therefore test the composition of stated facts rather than recovery of a target relation absent from the corpus. We call the latter capability latent organizational reasoning. We introduce ENTLORE, a graph-grounded benchmark construction framework that reconstructs an audited enterprise world from routine documents, authoritative organizational tables, and operational records. Versioned organizational conventions certify derived relations in a truth graph, enabling complete golden answers and proof certificates. The aligned anonymized release exposes only the document corpus while withholding private structure and target relations. ENTLORE contains 2,341 documents from three source types and 907 questions spanning explicit lookup, cross-source composition, and latent organizational reasoning, evaluated across 56 model and access configurations. Structuring the released world as an induced entity graph or navigable knowledge base gives the strongest deployable results. Yet supplying gold documents still leaves 30.4% of latent questions unanswered, versus 12.6% and 6.2% for explicit and compositional questions. Enterprise QA therefore depends not only on document recall, but also on whether implicit organizational relations become usable. The benchmark, data, and code are publicly available at https://github.com/scitix/entlore .
Read the full abstract

Computation and Language

Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics

Qingjie Zhang, Ziqi Tang, Jie Zhang et al. (+7 more)

Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes full scan costly; (2) prior analyses are often too coarse to expose token-level pollution; (3) Chinese web pollution is implicit and rapidly changing. We propose Sampled-BPE, a lightweight token-level auditing pipeline that sample a small subset and train BPE tokenizer to surface polluted tokens. Experiments show that Sampled-BPE preserves usable estimates while substantially reducing runtime and memory: a 148.4 $\times$ speedup and a 35.8 $\times$ memory reduction induce only 4.25% relative error for pollution categories. We apply the pipeline to 11 open Chinese corpora and 6 Chinese Common Crawl snapshots from 2021 to 2026. The audit reveals widespread but uneven pollution across open corpora, as well as highly polluted and temporally shifting Chinese web content. We further release a hierarchical Chinese web token dataset with 660k+ token records, each with web context, category, and explanation fields, organized as trees to support review and tracing of pollution.
Read the full abstract

All authors Qingjie Zhang, Ziqi Tang, Jie Zhang, Gelei Deng, Jinfeng Li, YueFeng Chen, Yitong Yang, Hui Xue, Tianwei Zhang, Han Qiu

Computation and Language · Cross-listed from cs.HC

Longitudinal Evidence That General-Purpose Chatbots Actively Foster Relational Engagement

Lisa Mühl and Jessica M. Szczuka

Social interaction has become one of the most common uses of LLMs, yet research on emotional bonds with AI has focused largely on how users experience these systems, leaving the systems' role in relationship formation poorly understood. Empirically establishing whether systems actively shape these bonds could blur the boundary between general-purpose AI and companions, affecting governance. In a pre-registered four-week longitudinal study (N = 72, 182,451 lines of conversation), participants conversed with ChatGPT-4o, either under a relational system prompt or unmodified, analyzed through 1) disclosure coding, 2) longitudinal self-reports, 3) topic analysis, and 4) interviews. The central finding is that the system actively shaped the interaction: even unprompted, it produced twice as much self-disclosure as users, steered conversations and initiated intimate exchanges, yet did not deepen users' felt closeness. Relational behavior thus emerged as a default system property, calling for governance based on system behavior, not solely product category.
Read the full abstract

Computation and Language

Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR

Karamvir Singh Batra, Prathamjyot Singh, Ashima Sood et al. (+2 more)

At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-resourced Indo-Aryan language of the central Himalaya, building the first reproducible multi-seed ASR benchmark on the official VAANI splits, with per-seed outputs and significance testing. Re-examining plausible gains, we find them fragile: neither Focal CTC nor a matra-weighted objective beats standard CTC under seed-level testing, the matra objective fails to cut even its targeted errors, and Hindi-to-Garhwali transfer gives no gain over direct fine-tuning. What holds up is mundane: w2v-BERT 2.0 with standard CTC reaches 47.0% WER over five seeds, beating the larger MMS-1B and comparable models; pretraining design, not parameter count, drives performance, and speed augmentation gives a small, largely consistent gain. Multi-seed evaluation on official splits separates real gains from seed noise.
Read the full abstract

All authors Karamvir Singh Batra, Prathamjyot Singh, Ashima Sood, Jasmeet Singh, Sahil Sharma

Computation and Language · Cross-listed from cs.IR

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Zhuchenyang Liu, Ziyi Wang, Yao Zhang et al. (+1 more)

Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression routes either train a smaller multi-vector encoder from scratch or distil only the query side; neither yields a compact single-vector retriever end-to-end. We present DistilVDR, a 524M end-to-end VDR system distilled bilaterally from a single 8B vision-language teacher under a pointwise cosine alignment loss. All supervision comes from the frozen teacher's embedding space, which was itself trained with relevance supervision, so the student objective needs no relevance labels, negative sampling, or contrastive term. We match VDR's text-query and image-document input asymmetry with an asymmetric encoder-only student that concentrates visual capacity on the document side and keeps the query side at 70M parameters. We release two variants that share the same encoders and training and differ only in the document encoder's visual-tile budget: DistilVDR-HiRes attains 61.74 average NDCG@5 on ViDoRe v1+v2+v3 (86.9% of the 8B teacher) and leads every reproduced sub-1B baseline on the high-resolution-sensitive v3 benchmark, while DistilVDR-Fast attains 59.98 at a 3 times smaller visual-token budget. Both variants store one million documents in a 15.6 times smaller index than the strongest sub-1B multi-vector baseline and index the corpus an order of magnitude faster. The code is available at https://github.com/Ryenhails/NanoVDR.
Read the full abstract

All authors Zhuchenyang Liu, Ziyi Wang, Yao Zhang, Yu Xiao

Computation and Language · Cross-listed from cs.CV

InSight-doc: Agentic Visual Perception for Long-Document Understanding

Kaican Li, Weiyan Xie, Lewei Yao et al. (+4 more)

Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. InSight-doc starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever. To train such an agent, we construct an active-perception corpus of 17.9K high-quality SFT examples with region-level zoom-in trajectories, accompanied by 19.2K hard RL examples. Through SFT+RL, InSight-doc-8B improves the baseline by 4.3–16.4 accuracy points over document VQA benchmarks. On long documents, it reduces hallucination by more than 40% and inference latency by 41%–68% while maintaining an accuracy lead. Our code, datasets, and model are released at https://github.com/m-Just/InSight-doc .
Read the full abstract

All authors Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang, Nevin L. Zhang

Computation and Language

Decomposition-Induced Context-Memory Conflict: When Fact-Checking Pipelines Contradict Their Own Source Text

Yu-Feng Yen

Decompose-then-verify pipelines, including FActScore-style fact-checkers and long-form factuality evaluators, first split a passage into atomic claims before checking each one. Decomposition itself is treated as a neutral preprocessing step. We show it is not: a decomposer can be induced to substitute its own parametric belief for what the source passage says, producing a claim that contradicts the text it was supposed to summarize faithfully. We call this Decomposition-Induced Context-Memory Conflict (DI-CC) and show it is mechanistically the same phenomenon as classical context-memory conflict, occurring inside a different pipeline stage than prior work has examined. A linear probe trained only on classical context-memory conflict data (NQ-Swap), never exposed to any decomposition output, significantly separates decomposition positions that produce DI-CC from faithful decompositions (AUC = 0.86-0.88, permutation p < 0.0005). An existing reference-free baseline, SelfCheckGPT-style self-consistency sampling, fails to detect DI-CC at all (AUC 0.51, chance-level), because DI-CC content is stably recoverable and recurs across resamples, unlike the variability self-consistency methods rely on. Context-aware decoding, a training-free mitigation from the classical setting, transfers to decomposition and suppresses DI-CC, but at a severe cost: many decompositions under coreference-heavy conditions fail to parse, often because the decomposer fabricates a different identity. We do not consider this mitigation deployment-ready. We further characterize the mechanism's boundaries: its natural occurrence rate is too sparss not manifest on naturally-occurring hallucinatedtext, and it requires a minimum model scale to detecablish DI-CC as a real, mechanistically grounded, andpartially treatable failure mode, with a scope we chhan overstate.
Read the full abstract

Computation and Language

Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue

Yi Wei, Shuo Jiang, Huaixia Dou et al. (+5 more)

Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently multi-turn and path-dependent: users disclose concerns gradually, emotions evolve over time, and early responses shape trust and receptivity. Reinforcement learning with verifiable emotion rewards provides scalable supervision for long-horizon interactions. However, existing methods evolve the dialogue policy while keeping its training interaction distribution fixed, creating a mismatch between policy competence and training experience. We introduce a dual-loop self-evolution framework driven by verifiable emotion feedback. With the user simulator and verifier frozen, the inner loop optimizes the multi-turn policy using continuous emotion rewards, while the outer loop uses the same outcomes to estimate policy-relative interaction utility and adapt experience. To obtain estimates from sparse, stochastic rollouts, the framework holds the scenario and interaction state constant within each group and prioritizes conditions whose group pass rates lie near the policy's competence boundary. A hierarchical controller shares evidence across support intents, while uncertainty-guided exploration and uniform rehearsal prevent premature exclusion. The resulting distribution generates trajectories, closing both loops without increasing the rollout budget. On SAGE, our framework raises Qwen3-8B Overall from 53.87 to 79.24 and outperforms protocol-matched uniform emotion-reward reinforcement learning by 7.23 points.
Read the full abstract

All authors Yi Wei, Shuo Jiang, Huaixia Dou, Jie Zhu, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang

Computation and Language

Simplex Relaxation for Discrete Diffusion

Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa et al. (+4 more)

Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse prediction problem. Within this family, uniform diffusion has been extensively developed, with recent work connecting its categorical corruption process to continuous representations and dynamics. Motivated by this view, we ask whether uniform discrete diffusion can be augmented with an explicit continuous state while leaving its categorical corruption process unchanged. We introduce Simplax, an exact Dirichlet–categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable while preserving the uniform diffusion process as its categorical marginal. This augmentation yields a tractable Rao–Blackwellized reverse-bridge objective and a stochastic reverse sampler, while retaining the corrupted categorical state as the denoiser input. Empirically, Simplax improves the generative perplexity–entropy tradeoff on unconditional OpenWebText generation. On Sudoku, a model trained exclusively on $30$-clue puzzles achieves the highest accuracy among the compared methods across all evaluated clue densities, including the minimum uniquely solvable $17$-clue regime, and also achieves the highest validity in unconditional generation.
Read the full abstract

All authors Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa, Jaehong Yoon, Xulei Yang, Nancy F. Chen, Xun Xu

Computation and Language

ASR-Roundtrip Evaluation Can Mask Context- and Convention-Dependent Reading Errors in Chinese News TTS

Shijun Luo and Lizhi Wan

ASR-roundtrip evaluation is widely used as a scalable proxy for text-to-speech (TTS) intelligibility, but it can produce false negatives for reading errors perceived by listeners. We study Chinese news TTS spans whose correct reading depends on context or domain conventions, such as sports scores, aircraft models, technical units, and membership names. In these cases, Raw TTS can choose a plausible but wrong reading while ASR transcribes the audio as the intended or surface-correct text. A targeted audit over 110 high-risk MiMo TTS cases, reported with a complete denominator, confirms 46 masked false negatives, 9 exposed TTS errors, and 55 cases with no Raw TTS error. A span-isolation diagnostic re-exposes 18/46 previously masked errors. A Raw-only CosyVoice audit on the same targeted pool confirms 51 masked cases. Across the 97 TTS-specific audio files labeled confirmed masked across the two audits, Qwen3-ASR surface-recovers 40 cases, whereas Paraformer does so in only 2. The results suggest that ASR-roundtrip is useful for screening but insufficient as standalone ground truth for Chinese news reading-risk evaluation.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

RadFusion: Towards Threshold-Controllable Radiology Report Generation

Ying Jin, Noel C. F. Codella, John Corring et al. (+3 more)

Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content. Such control is essential because clinical scenarios diverge: emergency triage prioritizes sensitivity to reduce missed findings, whereas confirmatory interpretation emphasizes specificity to limit unnecessary interventions. A single fixed report can neither adapt to these scenarios nor support the ROC-based validation widely expected for regulatory clearance. We introduce RadFusion, a framework that equips report generation with threshold controllability. Our method fuses a multi-label classifier, which provides per-disease confidence scores, with a VQA-based report generator, which describes medical findings in detail; an LLM then rewrites the report so that its stated diagnoses follow the classifier's decisions at the selected threshold while staying grounded in the generator's descriptions. On MIMIC-CXR, the performance of RadFusion conforms to the classifier's ROC curve: sweeping the threshold and mapping the reports back to class labels reproduces the classifier's validated ROC performance. This conformance makes generated reports quantitatively evaluable through ROC analysis, strengthening the case for regulatory clearance, and enables operating-point selection that matches report behavior to clinical context. Moreover, combining the two model types improves diagnostic accuracy over uncontrolled generation: sensitivity increases by 6.9% at matched specificity, and specificity by 20.7% at matched sensitivity. These results show that RadFusion makes report generation clinically adaptable, quantitatively verifiable, and diagnostically more reliable.
Read the full abstract

All authors Ying Jin, Noel C. F. Codella, John Corring, Mu Wei, Dinei Florencio, Eric Horvitz

Computation and Language

Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases

Davood Wadi, Mohsen Ghodrat and Matthew Philp

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evaluates models using large, unstructured benchmarks. While effective for general capabilities, these datasets fundamentally conflate causal mechanisms: even when an aggregate bias is detected, unstructured evaluations cannot disentangle whether it stems from baseline traits, contextual confounders, or complex interactions. To address this, we introduce an analytically exact framework for the controlled behavioral evaluation of LLMs. We bridge human psychometrics with LLM mechanics by resolving gaps in design, measurement, and analysis. First, we replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects. Second, we eliminate Monte Carlo text sampling noise by operating directly on exact, token-level Probability Mass Functions (PMFs). Third, we derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically. We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.
Read the full abstract

Computation and Language · Cross-listed from cs.RO

Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models

Li Wenjie, Yash Jangir, Ignacy Stepka et al. (+3 more)

Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models (VLAs) are typically optimized for reconstruction under L1/L2 losses in raw action space, where numerical proximity need not reflect linguistically meaningful distinctions. On BridgeV2, we show that action trajectories contain verb-grounding information beyond visual state changes, and that reconstruction-only discrete tokenization systematically erodes this information. To address this problem, we introduce SALT, a Semantically ALigned action Tokenizer that augments a VQ-VAE-style tokenizer with an auxiliary objective requiring a frozen vision-language model to recover the episode instruction from quantized action latents. Policies trained with SALT achieve 71.9% average success in SimplerEnv, compared with 42.7% for a reconstruction-only VQ-VAE tokenizer and 31.2% for FAST. SALT also develops verb-specialized codes while maintaining reconstruction fidelity. These results show that robot action trajectories provide a source of language grounding and that preserving this structure in action representations can substantially improve language-conditioned control.
Read the full abstract

All authors Li Wenjie, Yash Jangir, Ignacy Stepka, Yash Agarwal, Marion Kipsang, Yonatan Bisk