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 21 April

Computation and Language

CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks

Peiqin Lin, Chenyang Lyu, Wenjiang Luo et al. (+22 more)

Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks – where models must reason within real-world, context-rich scenarios – largely unaddressed. To fill this gap, we present CulturALL, a comprehensive and challenging benchmark to assess LLMs' multilingual and multicultural competence on grounded tasks. CulturALL is built via a human–AI collaborative framework: expert annotators ensure appropriate difficulty and factual accuracy, while LLMs lighten the manual workload. By incorporating diverse sources, CulturALL ensures comprehensive scenario coverage. Each item is carefully designed to present a high level of difficulty, making CulturALL challenging. CulturALL contains 2,610 samples in 14 languages from 51 regions, distributed across 16 topics to capture the full breadth of grounded tasks. Experiments show that the best LLM achieves 44.48% accuracy on CulturALL, underscoring substantial room for improvement.
Read the full abstract

All authors Peiqin Lin, Chenyang Lyu, Wenjiang Luo, Haotian Ye, Md Mehrab Hossain, Chunlan Ma, Shaoxiong Ji, Younes Samih, Bo Zeng, Fan Jiang, Yuanbin Cao, Dilda Duisenbek, Adrian Neo Sau Xun, Daria Pozdniakova, Liubou Misevich, Nevena Marinković, Ngoc Gia Linh Nguyen, Thi Khanh Linh Do, Sarakmatak Sophy, Baotian Hu, Guanhua Chen, Gongbo Tang, Alham Fikri Aji, Longyue Wang, Weihua Luo

Computation and Language

Towards a Linguistic Evaluation of Narratives: A Quantitative Stylistic Framework

Alessandro Maisto

The evaluation of narrative quality remains a complex challenge, as it involves subjective factors such as plot, character development, and emotional impact. This work proposes a quantitative approach to narrative assessment by focusing on the linguistic dimension as a primary indicator of quality. The paper presents a methodology for the automatic evaluation of narrative based on the extraction of a comprehensive set of 33 quantitative linguistic features categorized into lexical, syntactic, and semantic groups. To test the model, an experiment was conducted on a specialized corpus of 23 books, including canonical masterpieces and self-published works. Through a similarity matrix, the system successfully clustered the narratives, distinguishing almost perfectly between professionally edited and self-published texts. Furthermore, the methodology was validated against a human-annotated dataset; it significantly outperforms traditional story-level evaluation metrics, demonstrating the effectiveness of quantitative linguistic features in assessing narrative quality.
Read the full abstract

Computation and Language

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

Xianming Li, Zongxi Li, Tsz-fung Andrew Lee et al. (+3 more)

Popular low-rank parameter-efficient fine-tuning (PEFT) methods represent adaptation as separate updates to selected backbone weights, without maintaining an explicit task-specific state that is updated and reused across depth. These updates also require the backbone at inference and therefore cannot operate as standalone predictors. We propose ShadowPEFT, which consolidates trainable adaptation into a modular shadow component centered on a compact shadow model and lightweight Transformer layer-specific coupling modules. A persistent shadow state refines the frozen backbone representations and is updated from them in an interactive manner. Because the shadow model is trained as a complete predictor, it can be detached for shadow-only inference without executing the base model and can be initialized from a pretrained model. Experiments on text and image generation and understanding benchmarks show that ShadowPEFT matches or outperforms LoRA and DoRA under comparable trainable-parameter budgets. Additional analyses on shadow pretraining, cross-dataset transfer, parameter scaling, inference latency, and system-level evaluation suggest that centralized layer-space adaptation is a competitive and flexible alternative to conventional low-rank PEFT.
Read the full abstract

All authors Xianming Li, Zongxi Li, Tsz-fung Andrew Lee, Jing Li, Haoran Xie, Qing Li

Computation and Language

Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs

Clara Lachenmaier, Hannah Bultmann and Sina Zarrieß

Repair, an important resource for resolving trouble in human-human conversation, remains underexplored in human-LLM interaction. In this study, we investigate how LLMs engage in the interactive process of repair in multi-turn dialogues around solvable and unsolvable math questions. We examine whether models initiate repair themselves and how they respond to user-initiated repair. Our results show strong differences across models: reactions range from being almost completely resistant to (appropriate) repair attempts to being highly susceptible and easily manipulated. We further demonstrate that once conversations extend beyond a single turn, model behavior becomes more distinctive and less predictable across systems. Overall, our findings indicate that each tested LLM exhibits its own characteristic form of unreliability in the context of repair.
Read the full abstract

Computation and Language

Headlines You Won't Forget: Can Pronoun Insertion Increase Memorability?

Selina Meyer, Magdalena Abel and Michael Roth

For news headlines to influence beliefs and drive action, relevant information needs to be retained and retrievable from memory. In this probing study we draw on experiment designs from cognitive psychology to examine how a specific linguistic feature, namely direct address through first- and second-person pronouns, affects memorability and to what extent it is feasible to use large language models for the targeted insertion of such a feature into existing text without changing its core meaning. Across three controlled memorization experiments with a total of 240 participants, yielding 7,680 unique memory judgments, we show that pronoun insertion has mixed effects on memorability. Exploratory analyses indicate that effects differ based on headline topic, how pronouns are inserted and their immediate contexts. Additional data and fine-grained analysis is needed to draw definitive conclusions on these mediating factors. We further show that automatic revisions by LLMs are not always appropriate: Crowdsourced evaluations find many of them to be lacking in content accuracy and emotion retention or resulting in unnatural writing style. We make our collected data available for future work.
Read the full abstract

Computation and Language

SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization

Bo-Jyun Wang, Ying-Jia Lin and Hung-Yu Kao

Small language models (SLMs), such as BART, can achieve summarization performance comparable to large language models (LLMs) via distillation. However, existing LLM-based ranking strategies for summary candidates suffer from instability, while classical metrics (e.g., ROUGE) are insufficient to rank high-quality summaries. To address these issues, we introduce SCURank, a framework that enhances summarization by leveraging Summary Content Units (SCUs). Instead of relying on unstable comparisons or surface-level overlap, SCURank evaluates summaries based on the richness and semantic importance of information content. We investigate the effectiveness of SCURank in distilling summaries from multiple diverse LLMs. Experimental results demonstrate that SCURank outperforms traditional metrics and LLM-based ranking methods across evaluation measures and datasets. Furthermore, our findings show that incorporating diverse LLM summaries enhances model abstractiveness and overall distilled model performance, validating the benefits of information-centric ranking in multi-LLM distillation. The code for SCURank is available at https://github.com/IKMLab/SCURank.
Read the full abstract

Computation and Language

Mind the Unseen Mass: Unmasking LLM Hallucinations via Soft-Hybrid Alphabet Estimation

Hongxing Pan, Yingying Guo, Wenqing Kuang et al. (+1 more)

This paper studies uncertainty quantification for large language models (LLMs) under black-box access, where only a small number of responses can be sampled for each query. In this setting, estimating the effective semantic alphabet size–that is, the number of distinct meanings expressed in the sampled responses–provides a useful proxy for downstream risk. However, frequency-based estimators tend to undercount rare semantic modes when the sample size is small, while graph-spectral quantities alone are not designed to estimate semantic occupancy accurately. To address this issue, we propose SHADE (Soft-Hybrid Alphabet Dynamic Estimator), a simple and interpretable estimator that combines Generalized Good-Turing coverage with a heat-kernel trace of the normalized Laplacian constructed from an entailment-weighted graph over sampled responses. The estimated coverage adaptively determines the fusion rule: under high coverage, SHADE uses a convex combination of the two signals, while under low coverage it applies a LogSumExp fusion to emphasize missing or weakly observed semantic modes. A finite-sample correction is then introduced to stabilize the resulting cardinality estimate before converting it into a coverage-adjusted semantic entropy score. Experiments on pooled semantic alphabet-size estimation against large-sample references and on QA incorrectness detection show that SHADE achieves the strongest improvements in the most sample-limited regime, while the performance gap narrows as the number of samples increases. These results suggest that hybrid semantic occupancy estimation is particularly beneficial when black-box uncertainty quantification must operate under tight sampling budgets.
Read the full abstract

All authors Hongxing Pan, Yingying Guo, Wenqing Kuang, Jiashi Lu

Computation and Language

Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India

Kaushal Bhogale, Manas Dhir, Amritansh Walecha et al. (+11 more)

Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference WER penalizes natural spelling variation in Indian languages, including non standardized spellings of code-mixed English origin words. To address these limitations, we introduce Voice of India, a closed source benchmark built from unscripted telephonic conversations covering 15 major Indian languages across 139 regional clusters. The dataset contains 306230 utterances, totaling 536 hours of speech from 36691 speakers with transcripts accounting for spelling variations. We also analyze performance geographically at the district level, revealing disparities. Finally, we provide detailed analysis across factors such as audio quality, speaking rate, gender, and device type, highlighting where current ASR systems struggle and offering insights for improving real world Indic ASR systems.
Read the full abstract

All authors Kaushal Bhogale, Manas Dhir, Amritansh Walecha, Manmeet Kaur, Vanshika Chhabra, Aaditya Pareek, Hanuman Sidh, Mahima Manik, Sagar Jain, Bhaskar Singh, Utkarsh Singh, Tahir Javed, Shobhit Banga, Mitesh M. Khapra

Computation and Language

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning

Haoyang Chen, Yi Liu, Jianzhi Shao et al. (+3 more)

Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less understood how answer tokens actually read and integrate the reasoning to produce reliable outcomes. Focusing on quantitative reasoning, we analyze the answer-to-reasoning attention and observe a benign self-reading pattern aligned with correctness, characterized by a forward drift of the reading focus along the reasoning trace and a persistent concentration on key semantic anchors, whereas incorrect solutions exhibit diffuse and irregular attention pattern. We interpret this as internal certainty during answer decoding, where the model commits to a viable solution branch and integrates key evidence. Following this, we propose a training-free steering method driven by Self-Reading Quality (SRQ) scores combining geometric metrics for process control with semantic metrics for content monitoring. SRQ selects data to build steering vectors that guide inference toward benign self-reading and away from uncertain and disorganized reading. Experiments show that our method yields consistent accuracy gains.
Read the full abstract

All authors Haoyang Chen, Yi Liu, Jianzhi Shao, Tao Zhang, Chengfu Huo, Wei Hu

Computation and Language

ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation

Kunquan Li, Yingxue Zhang, Zhibin Lan et al. (+2 more)

Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). While most approaches adopt a 'pre-thinking' paradigm and benefit from explicit reasoning trajectories, they suffer from substantial inference cost and latency. To address these limitations, we propose ReflectMT, a two-stage reflection internalization framework for machine translation that employs a 'post-thinking' paradigm. Our approach develops the model's 'translate-reflect-refine' capability through reinforcement learning. In the first stage, we cultivate the model's capacity for high-quality reflection and refinement, thereby enhancing its semantic comprehension and task-specific knowledge. In the second stage, we train the model to internalize the knowledge acquired during reflection. On WMT24, ReflectMT achieves a GPT-4o-based GRF score of 86.16, outperforming DeepSeek-R1 (84.03) by 2.13 points, while using approximately 92% fewer output tokens. Independent automatic evaluation, a blinded human evaluation, and preliminary experiments on three additional translation directions provide further evidence for the framework's effectiveness.
Read the full abstract

All authors Kunquan Li, Yingxue Zhang, Zhibin Lan, Fandong Meng, Jinsong Su

Computation and Language

Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion

Shuai Wu, Xue Li, Zhijun Wang et al. (+4 more)

Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpretation depends on context: a conventional phrase may be useful, while a fluent answer may reinforce a false belief. This critical review examines linguistic habits and sycophancy across eight developer families: OpenAI, Anthropic, Google DeepMind, xAI, ByteDance, Moonshot AI, DeepSeek, and Xiaomi. We verify current public offerings against official release and API documentation, with an evidence cutoff of 1 October 2026. We synthesize research on lexical overrepresentation, stylistic variation, social warmth, and agreement, alongside benchmark methods and dated English and Chinese public discussions. The research reviewed documents recurring linguistic patterns and agreement that distorts judgment; comparable measurements of the newest releases are sparse in the retrieved set. Current user reports include both complaints and improved writing, with experiences varying by task and prompting. We propose separate measures of recurrence, contextual appropriateness, and belief distortion, with precise service records and language-specific annotation. This framework makes claims about writing quality and conversational reliability testable as model services change.
Read the full abstract

All authors Shuai Wu, Xue Li, Zhijun Wang, Bolun Liu, Weilin Cai, Zihao Su, Ran Wang

Computation and Language

Construction of Knowledge Graph based on Language Model

Qiubai Zhu, Qingwang Wang, Haibin Yuan et al. (+2 more)

Knowledge Graph (KG) can effectively integrate valuable information from massive data, and thus has been rapidly developed and widely used in many fields. Traditional KG construction methods rely on manual annotation, which often consumes a lot of time and manpower. And KG construction schemes based on deep learning tend to have weak generalization capabilities. With the rapid development of Pre-trained Language Models (PLM), PLM has shown great potential in the field of KG construction. This paper provides a comprehensive review of recent research advances in the field of construction of KGs using PLM. In this paper, we explain how PLM can utilize its language understanding and generation capabilities to automatically extract key information for KGs, such as entities and relations, from textual data. In addition, We also propose a new Hyper-Relarional Knowledge Graph construction framework based on lightweight Large Language Model (LLM) named LLHKG and compares it with previous methods. Under our framework, the KG construction capability of lightweight LLM is comparable to GPT3.5.
Read the full abstract

All authors Qiubai Zhu, Qingwang Wang, Haibin Yuan, Wei Chen, Tao Shen

Computation and Language

Do Emotions Influence Moral Judgment in Large Language Models?

Mohammad Saim and Tianyu Jiang

Large language models have been extensively studied for emotion recognition and moral reasoning as distinct capabilities, yet the extent to which emotions influence moral judgment remains underexplored. In this work, we develop an emotion-induction pipeline that infuses emotion into moral situations and evaluate shifts in moral acceptability across multiple datasets and LLMs. We observe a directional pattern: positive emotions increase moral acceptability and negative emotions decrease it, with effects strong enough to reverse binary moral judgments in up to 20% of cases, and with susceptibility scaling inversely with model capability. Our analysis further reveals that specific emotions can sometimes behave contrary to what their valence would predict (e.g., remorse paradoxically increases acceptability). A complementary human annotation study shows humans do not exhibit these systematic shifts, indicating an alignment gap in current LLMs.
Read the full abstract

Computation and Language

Detoxification for LLM: From Dataset Itself

Wei Shao, Yihang Wang, Gaoyu Zhu et al. (+4 more)

Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches cannot completely suppress the model's inherent toxicity, whereas detoxifying the pretraining dataset can fundamentally reduce the toxicity that the model learns during training. Hence, we attempt to detoxify directly on raw corpora with SoCD (Soft Contrastive Decoding), which guides an LLM to localize and rewrite toxic spans in raw data while preserving semantics, in our proposed HSPD (Hierarchical Semantic-Preserving Detoxification) pipeline, yielding a detoxified corpus that can drop-in replace the original for fine-tuning or other training. On GPT2-XL, HSPD attains state-of-the-art detoxification, reducing Toxicity Probability (TP) from 0.42 to 0.18 and Expected Maximum Toxicity (EMT) from 0.43 to 0.20. We further validate consistent best-in-class results on LLaMA2-7B, OPT-6.7B, and Falcon-7B. These findings show that semantics-preserving, corpus-level rewriting with HSPD effectively suppresses downstream toxicity while retaining data utility and allowing seamless source-level mitigation, thereby reducing the cost of later model behavior adjustment. (Code is available at: https://github.com/ntsw2001/data_detox_for_llm)
Read the full abstract

All authors Wei Shao, Yihang Wang, Gaoyu Zhu, Ziqiang Cheng, Lei Yu, Jiafeng Guo, Xueqi Cheng

Computation and Language

SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning

Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl et al. (+12 more)

English financial NLP has advanced rapidly through benchmarks targeting earnings analysis, market sentiment, tabular reasoning, and financial question answering, yet Arabic financial NLP remains virtually nonexistent, despite 422 million speakers, $4.9 trillion in Gulf sovereign wealth, and a $4-5 trillion Islamic finance industry requiring specialized Shari'ah compliance over instruments like sukuk, murabaha, and takaful. We introduce Sahm, the first Arabic financial benchmark spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause reasoning, comprising 14,380 expert-verified instances from authentic regulatory, juristic, and corporate sources. Evaluating 20 LLMs, we find Arabic fluency does not imply financial reasoning: models achieving 91% on recognition tasks drop sharply on generation, and event-cause reasoning exposes the widest performance gap (1.89-9.84/10). We release the benchmark and dataset to support trustworthy Arabic financial assistants.
Read the full abstract

All authors Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie

Computation and Language · Cross-listed from eess.AS

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization

Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan et al. (+3 more)

Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified ASR framework for Transducer (RNNT) training that supports both offline and streaming decoding within a single model, using chunk-limited attention with right context and dynamic chunked convolutions. To further close the gap between offline and streaming performance, we introduce an efficient Triton implementation of mode-consistency regularization for RNNT (MCR-RNNT), which encourages agreement across training modes. Experiments show that the proposed approach improves streaming accuracy at low latency while preserving offline performance and scaling to larger model sizes and training datasets. The proposed Unified ASR framework and the English model checkpoint are open-sourced.
Read the full abstract

All authors Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Nune Tadevosyan, Vitaly Lavrukhin, Boris Ginsburg

Computation and Language

HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo et al. (+7 more)

Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics. LLM's performance in thousand-words level and open-ended writing is inadequately assessed by traditional reference-based metrics or modern LLM-as-a-judge methods. We propose Tree-of-Writing (ToW), to resolve the implicit inconsistency often found when LLM-as-a-judge aggregates all sub-features in text evaluation. ToW incorporates a tree-structured workflow by explicitly modeling the aggregation weights of sub-features. We also present HowToBench, a large-scale Chinese writing benchmark encompassing 12 genres and 1302 instructions across three task categories: contextual completion, outline-guided writing, and open-ended generation. ToW successfully mitigates the biases, achieving a 0.93 Pearson correlation with human judgments. Furthermore, we detect that both overlap-based text generation metrics and popular LLM-as-a-judge practices are vulnerable to textual disturbances, while ToW is robust to them. We also uncover a negative correlation between input length and content-related scores in the Guide task, showcasing that it cannot be simply improved by input-side information piling.
Read the full abstract

All authors Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Lin Fan, Yilin Zhou, Zikang Wang, Xiaotao Gu, Jie Tang, Hongning Wang, Minlie Huang

Computation and Language

TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only

Yilun Liu, Ruihong Qiu and Zi Huang

Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision. While graph neural networks rely on fixed label spaces and supervised objectives, recent large language model (LLM)-based approaches often overlook graph context or depend on distillation from larger models, limiting generalisation. We propose TRN-R1-Zero, a post-training framework for TRN reasoning trained solely via reinforcement learning. TRN-R1-Zero directly optimises base LLMs using a Neighbour-aware Group Relative Policy Optimisation objective that dynamically adjusts rewards based on a novel margin gain metric for the informativeness of neighbouring signals, effectively guiding the model toward relational reasoning. Unlike prior methods, TRN-R1-Zero requires no supervised fine-tuning or chain-of-thought data generated from large reasoning models. Extensive experiments across citation, hyperlink, social and co-purchase TRN benchmarks demonstrate the superiority and robustness of TRN-R1-Zero. Moreover, relying strictly on node-level training, TRN-R1-Zero achieves zero-shot inference on edge- and graph-level tasks, extending beyond cross-domain transfer. The codebase is publicly available at https://github.com/superallen13/TRN-R1-Zero.
Read the full abstract

Computation and Language

Product-of-Experts Training Reduces Dataset Artifacts in Natural Language Inference

Aby Mammen Mathew

Neural NLI models overfit dataset artifacts instead of truly reasoning. A hypothesis-only model gets 57.7% in SNLI, showing strong spurious correlations, and 38.6% of the baseline errors are the result of these artifacts. We propose Product-of-Experts (PoE) training, which downweights examples where biased models are overconfident. PoE nearly preserves accuracy (89.10% vs. 89.30%) while cutting bias reliance by 4.71% (bias agreement 49.85% to 45%). An ablation finds lambda = 1.5 that best balances debiasing and accuracy. Behavioral tests still reveal issues with negation and numerical reasoning.
Read the full abstract

Computation and Language

Cell-Based Representation of Relational Binding in Language Models

Qin Dai, Benjamin Heinzerling and Kentaro Inui

Understanding a discourse requires tracking entities and the relations that hold between them. While Large Language Models (LLMs) perform well on relational reasoning, the mechanism by which they bind entities, relations, and attributes remains unclear. We study discourse-level relational binding and show that LLMs encode it via a Cell-based Binding Representation (CBR): a low-dimensional linear subspace in which each “cell” corresponds to an entity–relation index pair, and bound attributes are retrieved from the corresponding cell during inference. Using controlled multi-sentence data annotated with entity and relation indices, we identify the CBR subspace by decoding these indices from attribute-token activations with Partial Least Squares regression. Across domains and two model families, the indices are linearly decodable and form a grid-like geometry in the projected space. We further find that context-specific CBR representations are related by translation vectors in activation space, enabling cross-context transfer. Finally, activation patching shows that manipulating this subspace systematically changes relational predictions and that perturbing it disrupts performance, providing causal evidence that LLMs rely on CBR for relational binding.
Read the full abstract

Computation and Language

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning

Boyan Shi, Wei Chen, Shuyuan Zhao et al. (+4 more)

The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges: (1)Imprecise Routing in the current MoE-LoRA method fails to explicitly match input semantics with expert capabilities, leading to weak expert specialization. (2)Uniform weight fusion strategies struggle to provide adaptive update strengths, overlooking the varying complexity of different tasks. To address these limitations, we propose SAMoRA (Semantic-Aware Mixture of LoRA Experts), a novel parameter-efficient fine-tuning framework tailored for task-adaptive learning. Specifically, A Semantic-Aware Router is proposed to explicitly align textual semantics with the most suitable experts for precise routing. A Task-Adaptive Scaling mechanism is designed to regulate expert contributions based on specific task requirements dynamically. In addition, a novel regularization objective is proposed to jointly promote expert specialization and effective scaling. Extensive experiments on multiple multi-task benchmarks demonstrate that SAMoRA significantly outperforms the state-of-the-art methods and holds excellent task generalization capabilities. Code is available at https://github.com/boyan-code/SAMoRA
Read the full abstract

All authors Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan

Computation and Language

RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora

Hanjun Cho and Jay-Yoon Lee

Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity. This mismatch undermines evaluation validity: retrievers can be unfairly undervalued even when they retrieve documents that provide sufficient evidence, because redundancy across documents is not accounted for in evaluation. On the other hand, retrievers that perform well on standard benchmarks often generalize poorly to real-world corpora with highly similar and redundant documents. We present RARE (Redundancy-Aware Retrieval Evaluation), a framework for constructing realistic benchmarks by (i) decomposing documents into atomic facts to enable precise redundancy tracking and (ii) enhancing LLM-based data generation with CRRF. RAG benchmark data usually requires multiple quality criteria, but LLMs often yield trivial outputs. CRRF scores criteria separately and fuses decisions by rank, improving the reliability of generated data. Applying RARE to Finance, Legal, and Patent corpora, we introduce RedQA, where a strong retriever baseline drops from 66.4% PerfRecall@10 on 4-hop General-Wiki to 5.0-27.9% PerfRecall@10 at 4-hop depth, revealing robustness gaps that current benchmarks fail to capture. RARE enables practitioners to build domain-specific RAG evaluations that faithfully reflect real-world deployment conditions.
Read the full abstract

Computation and Language

AlignCultura: Towards Culturally Aligned Large Language Models?

Gautam Siddharth Kashyap, Mark Dras and Usman Naseem

Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, models risk generating stereotyped, insensitive, or misleading responses that fail to reflect cultural diversity w.r.t Helpful, Harmless, and Honest (HHH) paradigm. Existing benchmarks represent early steps toward cultural alignment; yet, no benchmarks currently enables systematic evaluation of cultural alignment in line with UNESCO's principles of cultural diversity w.r.t HHH paradigm. Therefore, to address this gap, we built Align-Cultura, two-stage pipeline for cultural alignment. Stage I constructs CULTURAX, the HHH-English dataset grounded in the UNESCO cultural taxonomy, through Query Construction, which reclassifies prompts, expands underrepresented domains (or labels), and prevents data leakage with SimHash. Then, Response Generation pairs prompts with culturally grounded responses via two-stage rejection sampling. The final dataset contains 1,500 samples spanning 30 subdomains of tangible and intangible cultural forms. Stage II benchmarks CULTURAX on general-purpose models, culturally fine-tuned models, and open-weight LLMs (Qwen3-8B and DeepSeek-R1-Distill-Qwen-7B). Empirically, culturally fine-tuned models improve joint HHH by 4%-6%, reduce cultural failures by 18%, achieve 10%-12% efficiency gains, and limit leakage to 0.3%.
Read the full abstract

Computation and Language

Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

Yixuan Tang, Yirui Zhang, Hang Feng et al. (+1 more)

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.
Read the full abstract

All authors Yixuan Tang, Yirui Zhang, Hang Feng, Anthony K.H. Tung

Computation and Language

HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces

Ishita Kakkar, Enze Zhang, Rheeya Uppaal et al. (+1 more)

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but unfolds through distinct behavioral steps such as suppressing refusal, rationalizing compliance, decomposing harmful tasks, and concealing risk. However, no existing benchmark captures this process at sentence-level granularity within reasoning traces – a key step toward reliable safety monitoring, interventions, and systematic failure diagnosis. To address this gap, we introduce HarmThoughts, a benchmark for step-wise safety evaluation of reasoning traces. HarmThoughts is built around our proposed harm taxonomy, comprising 16 functional reasoning behavior categories that capture how reasoning steps contribute to or mitigate harmful outcomes. The dataset consists of 56,931 sentences from 1,018 reasoning traces generated by four model families, each annotated with fine-grained sentence-level behavioral labels. Using HarmThoughts, we analyze harm propagation by composing taxonomy behaviors into safety-failure patterns that characterize how reasoning transitions into harmful execution. We compare white-box and black-box monitors for identifying fine-grained taxonomy behaviors, and further evaluate supervised fine-tuning. While off-the-shelf monitors degrade sharply as behavioral granularity increases, fine-tuning substantially improves performance, highlighting both the difficulty and learnability of fine-grained process-level safety monitoring.
Read the full abstract

All authors Ishita Kakkar, Enze Zhang, Rheeya Uppaal, Junjie Hu

Computation and Language

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Zhenbang Du, Kejing Xia, Xinrui Zhong et al. (+6 more)

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redundancy caused by confidence clusters and positional ambiguity, and temporal redundancy caused by repeatedly remasking predictions that have already stabilized. Motivated by these patterns, we propose $R^{2}$-dLLM, a unified framework for reducing decoding redundancy from both inference and training perspectives. At inference time, we introduce training-free decoding rules that aggregate local confidence and token predictions, and finalize temporally stable tokens to avoid redundant decoding steps. We further propose a redundancy-aware supervised fine-tuning pipeline that aligns the model with efficient decoding trajectories and reduces reliance on manually tuned thresholds. Experiments demonstrate that $R^{2}$-dLLM consistently reduces the number of decoding steps by up to 88% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks. These results validate that decoding redundancy is a central bottleneck in dLLMs, and that explicitly reducing it yields substantial practical efficiency gains. Our code and models are available at https://github.com/GATECH-EIC/R2-dLLM.
Read the full abstract

All authors Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin

Computation and Language

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming

MinJae Jung, YongTaek Lim, Chaeyun Kim et al. (+3 more)

While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Teaming, a novel black-box framework for automated red teaming that effectively generates such prompts. STAR-Teaming integrates a Multi-Agent System (MAS) with a Strategy-Response Multiplex Network and employs network-driven optimization to sample effective attack strategies. This network-based approach recasts the intractable high-dimensional embedding space into a tractable structure, yielding two key advantages: it enhances the interpretability of the LLM's strategic vulnerabilities, and it streamlines the search for effective strategies by organizing the search space into semantic communities, thereby preventing redundant exploration. Empirical results demonstrate that STAR-Teaming significantly surpasses existing methods, achieving a higher attack success rate (ASR) at a lower computational cost. Extensive experiments validate the effectiveness and explainability of the Multiplex Network. The code is available at https://github.com/selectstar-ai/STAR-Teaming-paper.
Read the full abstract

All authors MinJae Jung, YongTaek Lim, Chaeyun Kim, Junghwan Kim, Kihyun Kim, Minwoo Kim

Computation and Language

Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest

Ramtin Davoudi, Kartik Thakkar, Nazanin Donyapour et al. (+2 more)

In this study, we present the first comprehensive evaluation of modern LLMs - including GPT-4, GPT-4o, GPT-3.5-Turbo, Gemini 1.5 Pro, DeepSeek-V3, Llama 3.2, and BERT - across three core social media analytics tasks on a Twitter (X) dataset: (I) Social Media Authorship Verification, (II) Social Media Post Generation, and (III) User Attribute Inference. For the authorship verification, we introduce a systematic sampling framework over diverse user and post selection strategies and evaluate generalization on newly collected tweets from January 2024 onward to mitigate "seen-data" bias. For post generation, we assess the ability of LLMs to produce authentic, user-like content using comprehensive evaluation metrics. Bridging Tasks I and II, we conduct a user study to measure real users' perceptions of LLM-generated posts conditioned on their own writing. For attribute inference, we annotate occupations and interests using two standardized taxonomies (IAB Tech Lab 2023 and 2018 U.S. SOC) and benchmark LLMs against existing baselines. Overall, our unified evaluation provides new insights and establishes reproducible benchmarks for LLM-driven social media analytics. The code and data are provided in the supplementary material and will also be made publicly available upon publication.
Read the full abstract

All authors Ramtin Davoudi, Kartik Thakkar, Nazanin Donyapour, Tyler Derr, Hamid Karimi

Computation and Language · Cross-listed from cs.MA

Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems

Namyoung So, Seokgyu Jang and Taeuk Kim

Adaptive multi-agent systems (MAS) are increasingly adopted to tackle complex problems. However, the narrow task coverage of their optimization raises the question of whether they can function as general-purpose systems. To address this gap, we conduct an extensive empirical study of adaptive MAS, revealing two key findings: (1) topological overfitting – they fail to generalize across different domains; and (2) illusory coordination – they achieve reasonable surface-level accuracy while the underlying agent interactions diverge from ideal MAS behavior, raising concerns about their practical utility. These findings highlight the pressing need to prioritize generalization in MAS development and motivate evaluation protocols that extend beyond simple final-answer correctness. We release our code at this https URL.
Read the full abstract

Computation and Language

A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition

Jiang Xiaobo, Dinghong Lai, Song Qiu et al. (+2 more)

Named Entity Recognition (NER) models trained on clean, high-resource corpora exhibit catastrophic performance collapse when deployed on noisy, sparse User-Generated Content (UGC), such as social media. Prior research has predominantly focused on point-wise symptom remediation – employing customized fine-tuning to address issues like neologisms, alias drift, non-standard orthography, long-tail entities, and class imbalance. However, these improvements often fail to generalize because they overlook the structural sparsity inherent in UGC. This study reveals that surface-level noise symptoms share a unified root cause: low Information Density (ID). Through hierarchical confounding-controlled resampling experiments (specifically controlling for entity rarity and annotation consistency), this paper identifies ID as an independent key factor. We introduce Attention Spectrum Analysis (ASA) to quantify how reduced ID causally leads to “attention blunting,” ultimately degrading NER performance. Informed by these mechanistic insights, we propose the Window-Aware Optimization Module (WOM), an LLM-empowered, model-agnostic framework. WOM identifies information-sparse regions and utilizes selective back-translation to directionally enhance semantic density without altering model architecture. Deployed atop mainstream architectures on standard UGC datasets (WNUT2017, Twitter-NER, WNUT2016), WOM yields up to 4.5% absolute F1 improvement, demonstrating robustness and achieving new state-of-the-art (SOTA) results on WNUT2017.
Read the full abstract

All authors Jiang Xiaobo, Dinghong Lai, Song Qiu, Yadong Deng, Xinkai Zhan