论文检索

Jueon Park, WonJune Jang, Chanhwi Kim, Yein Park, Jaewoo Kang

Recent advances in large language models (LLMs) have enabled molecular reasoning for property prediction. However, toxicity arises from complex biological mechanisms beyond chemical structure, necessitating mechanistic reasoning for reliable prediction. Despite its importance, current benchmarks fail to systematically evaluate this capability. LLMs can generate fluent but biologically unfaithful explanations, making it difficult to assess whether predicted toxicities are grounded in valid mechanisms. To bridge this gap, we introduce ToxReason, a benchmark grounded in the Adverse Outcome Pathway (AOP) that evaluates organ-level toxicity reasoning across multiple organs. ToxReason integrates experimental drug–target interaction evidence with toxicity labels, requiring models to infer both toxic outcomes and their underlying mechanisms from Molecular Initiating Event (MIE) to Adverse Outcome (AO). Using ToxReason, we evaluate toxicity prediction performance and reasoning quality across diverse LLMs. We find that strong predictive performance does not necessarily imply reliable reasoning. Furthermore, we show that reasoning-aware training improves mechanistic reasoning and, consequently, toxicity prediction performance. Together, these results underscore the necessity of integrating reasoning into both evaluation and training for trustworthy toxicity modeling.

Shuanghong Huang, Jinlei Xu, Youchao Zhou, Yanghao Zhou, Xuan Zhao, Chong Feng, Wenxuan Zhang

Large Audio-Language Models (LALMs) have demonstrated strong performance in spoken question answering (QA), with existing evaluations primarily focusing on answer accuracy and robustness to acoustic perturbations. However, such evaluations implicitly assume that spoken inputs remain semantically answerable, an assumption that often fails in real-world interaction when essential information is missing. In this work, we introduce a repair-aware evaluation setting that explicitly distinguishes between answerable and unanswerable audio inputs. We define answerability as a property of the input itself and construct paired evaluation conditions using a semantic-acoustic masking protocol. Based on this setting, we propose the Evaluability Awareness and Repair (EAR) score, a non-compensatory metric that jointly evaluates task competence under answerable conditions and repair behavior under unanswerable conditions. Experiments on two spoken QA benchmarks across diverse LALMs reveal a consistent gap between answer accuracy and conversational reliability: while many models perform well when inputs are answerable, most fail to recognize semantic unanswerability and initiate appropriate conversational repair. These findings expose a limitation of prevailing accuracy-centric evaluation practices and motivate reliability assessments that treat unanswerable inputs as cues for repair and continued interaction. The core code and dataset are publicly available at https://github.com/sheunghung/EAR.

Ganghao Liu, Qin Zhou, Zhe Wang, Xuehan Lu, Haihua Huang, Yunfei Tong, Heng Tian

Parameter-efficient fine-tuning (PEFT) enables low-cost adaptation of large language models but often suffers from limited representational flexibility. To address this, we incorporate a Mixture-of-Experts (MoE) design and propose Efficient and Expressive split-path experts that enhance specialization while maintaining low resource overhead. Split-Path Adaptive Representation Mixture-of-Experts (SparMoE) replaces discrete hard routing with a soft routing and fully-activated mixture, enabling stable optimization. Each expert is parameterized as a split-path modulation module, consisting of a scaling path that promotes expert specialization and a bias path that preserves expert-specific signals. This design significantly enhances expressive capacity while maintaining strict parameter efficiency and architectural compatibility with PEFT. Extensive evaluations on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk show that our approach consistently outperforms or matches state-of-the-art PEFT methods under comparable parameter budgets, achieving a favorable trade-off between adaptability and efficiency.

Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu

Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As content formats evolve, hate speech is transitioning from solely plain text to complex multimodal expressions, making implicit attacks harder to spot. Current systems, however, often falter on these subtle cases, as they struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. To bridge this gap, we move beyond binary classification to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. Guided by this fine-grained formulation, we curate the Hate via Vision-Language Interplay (H-VLI) benchmark where the true intent hinges on the intricate interplay of modalities rather than overt visual or textual slurs. To effectively decipher these complex cues, we further propose the Asymmetric Reasoning via Courtroom Agent DEbate (ARCADE) framework. By simulating a judicial process where agents actively argue for accusation and defense, ARCADE forces the model to scrutinize deep semantic cues before reaching a verdict. Extensive experiments demonstrate that ARCADE significantly outperforms state-of-the-art baselines on H-VLI, particularly for challenging implicit cases, while maintaining competitive performance on established benchmarks. Our code and data are available at:https://github.com/Sayur1n/H-VLI

Hongtao Duan, Lu Jiang, Minying Zhang, Xiaobing Zhu, Tianpeng Bu, Hao Jiang, Xinyu Wei, Lulu hu

Tool calling requires Large Language Models (LLMs) to generate structured decisions including tool names and schema-constrained arguments, where small decoding mistakes can cause hard failures. Existing methods either rely on costly tool-use training data or only constrain syntax, leaving tool selection and argument value errors largely unsolved. We analyze tool calling failures through a Where–When lens: (Where) failures correlate with persistent uncertainty in late transformer layers, (When) uncertainty concentrates on content-bearing tokens (tool names and argument values) rather than schema tokens. Based on this, and motivated by evidence that transformer Feed Forward Networks (FFNs) act as key–value style memories that store and retrieve factual or associative mappings, we propose Memory Space Tool Retracing (MemTR), a weight-free decoding-time method that retrieves relevant tool evidence from the tool library and mixes it into the FFN-output at the uncertain layer, treating FFNs as key–value memories. Through extensive experiments on various model families (Qwen, Llama, and xLAM) and benchmarks (BFCL, ACEBench, APIBank), MemTR reduces tool calling failures by 2%–9% with only 1%–2% runtime overhead, without any fine-tuning or additional tool-use training data.

Tian Bai, Huiyan Ying, Kailong Suo, Victor Junqiu Wei, Tao Fan, Yuanfeng Song

This paper introduces the **Text-to-TrajVis** task, which aims to transform natural language questions into trajectory data visualizations, facilitating the development of natural language interfaces for trajectory visualization systems. As this is a novel task, there is currently no relevant dataset available in the community. To address this gap, we first devised a new visualization language called Trajectory Visualization Language (TVL) to facilitate querying trajectory data and generating visualizations. Building on this foundation, we further proposed a dataset construction method that integrates Large Language Models (LLMs) with human efforts to create high-quality data. Specifically, we devised a four-stage pipeline that begins with candidate extraction, proceeds through seed TVL generation and tree-based expansion, and concludes with LLM-driven question creation followed by human validation. This process results in the creation of the first large-scale Text-to-TrajVis dataset, named **TrajVL**, which contains 9,608 (question, TVL) pairs. We propose a framework called **TRCAT** for progressively converting natural language questions into TVLs. The framework incorporates TVL-RAG Chain Module and Area-Time Standardization Module, significantly enhancing the accuracy of LLMs in TVL generation. Based on the TrajVL dataset, we conduct a comprehensive evaluation of TRCAT’s performance across several mainstream LLMs (e.g., GPT, Qwen, LLaMA, and Gemma). Furthermore, we established a benchmarking system for this task, providing a foundation for future research in structured trajectory language generation.

Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Bibo Cai, Yang Zhao, Bing Qin, Ting Liu

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs. Given that real-world data samples are typically confounded by a wide range of biases, LLMs tend to exhibit unstable performance when deployed in high-stakes real-world scenarios such as clinical diagnosis and legal document analysis. However, previous benchmarks are constrained to datasets where each sample is manually injected with only one type of bias. To bridge this gap, we propose a multi-bias benchmark where each sample contains multiple types of biases. Experimental results reveal that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating such compounded biases.

Haonan Chen, Sicheng Gao, Radu Timofte, Tetsuya Sakai, Zhicheng Dou

Modern information systems often involve different types of items, , a text query, an image, a video clip, or an audio segment. This motivates omni-modal embedding models that map heterogeneous modalities into a shared space for direct comparison. However, most recent omni-modal embeddings still rely heavily on implicit alignment inherited from pretrained vision-language model (VLM) backbones. In practice, this causes three common issues: (i) similarity logits have modality-dependent sharpness, so scores are not on a consistent scale; (ii) in-batch negatives become less effective over time because mixed-modality batches create an imbalanced hardness distribution; as a result, many negatives quickly become trivial and contribute little gradient; and (iii) embeddings across modalities show mismatched first- and second-order statistics, which makes rankings less stable. To tackle these problems, we propose e5-omni, a lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. e5-omni combines three simple components: (1) modality-aware temperature calibration to align similarity scales, (2) a controllable negative curriculum with debiasing to focus on confusing negatives while reducing the impact of false negatives, and (3) batch whitening with covariance regularization to better match cross-modal geometry in the shared embedding space. Experiments on MMEB-V2 and AudioCaps show consistent gains over strong bi-modal and omni-modal baselines, and the same recipe also transfers well to other VLM backbones. We release our model checkpoint at https://huggingface.co/collections/Haon-Chen/e5-omni.

Yanlin Wang, Bowen Zhang, Yanli Wang, Daya Guo, Terry Yue Zhuo, Jiachi Chen, Mingwei Liu, Xingong Zhang, Zibin Zheng

ArkTS is the primary programming language for Huawei’s HarmonyOS ecosystem, which has expanded across smartphones, tablets, and IoT devices. While large language models have demonstrated strong code generation capabilities for mainstream languages, their performance on ArkTS remains largely unexplored. To address this gap, we introduce ArkRepoBench, the first repository-level code completion benchmark for ArkTS to our knowledge, 7,519 samples from 20 official HarmonyOS repositories. The benchmark covers multiple difficulty levels and further categorizes completion instances into Single-File, Cross-File Independent, and Cross-File Dependent settings based on dependency analysis, distinguishing the mere presence of cross-file context from its actual necessity. Our experiments show that: (1) ArkTS completion consistently underperforms mainstream languages under our experimental settings, suggesting language-specific challenges associated with this emerging language; (2) open-source 7B models achieve performance comparable to close-source models; (3) cross-file context is a double-edged sword, with sparse retrieval(Jaccard) outperforming dense methods on ArkTS; and (4) HarmonyOS API documentation consistently improves performance, suggesting the benefits of domain-specific enhancements in low-resource settings.

Xueran Han, Yuhan Liu, Mingzhe Li, Wei Liu, Sen Hu, Rui Yan, Zhiqiang xu, Xiuying Chen

Great novels create immersive worlds with rich character arcs, well-structured plots, and nuanced writing styles. However, current novel generation methods often rely on brief, simplistic story outlines and generate details using plain, generic language.To bridge this gap, we introduce the task of \textit{Imitative Novel Generation}, which requires the generated novels to imitate the distinctive features of the original work, including understanding character profiles and world views, predicting plausible plot developments, and writing concrete details using vivid, expressive language.To achieve this, we propose WriterAgent, a novel generation system designed to master the core aspects of literary imitative.WriterAgent is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. Its key tasks include language style learning, character modeling, plot planning, and stylish writing, ensuring comprehensive narrative control.To support this, WriterAgent leverages the WriterLoRA framework, an extension of LoRA with hierarchical and cumulative task-specific modules, each specializing in a different narrative aspect. We evaluate WriterAgent on multilingual classics like \textit{Harry Potter} and \textit{Dream of the Red Chamber}, demonstrating its superiority over baselines in capturing the target author’s settings, character dynamics, and writing style to produce coherent, faithful narratives.We hope this work inspires literary creativity in NLP: {WriterAgent}.

Linhao Zhang, Yuhan Song, Aiwei Liu, Chuhan Wu, Sijun Zhang, Wei Jia, Yuan Liu, Houfeng Wang, Zhou Xiao

Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental limitation of ASR-centric training, which provides precise linguistic targets but implicitly teaches models to suppress paralinguistic cues and acoustic events as noise. To address this, we propose Unified Audio Schema (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components—Transcription, Paralinguistics, and Non-linguistic Events—within a unified JSON format. This design achieves comprehensive acoustic coverage without sacrificing the tight audio-text alignment that enables reasoning. We validate the effectiveness of this supervision strategy by applying it to both discrete and continuous AudioLLM architectures. Extensive experiments on MMSU, MMAR, and MMAU demonstrate that UAS-Audio yields consistent improvements, boosting fine-grained perception by 10.9% on MMSU over the same-size state-of-the-art models while preserving robust reasoning capabilities. Our code and model are publicly available at https://github.com/Tencent/Unified_Audio_Schema.

Ruixuan Xu, Jiexi Xu, Qiyan Zhao, Xiaofeng Zhang

Recent advances in diffusion-based Multimodal Large Language Models (dMLLMs) offer a compelling alternative to autoregressive counterparts; however, they remain prone to hallucinations. Through information flow analysis on LLaDA-V, we identify two intertwined factors contributing to this issue. First, although the special tokens serve as semantic anchors for aggregating visual information, they simultaneously induce severe attention sinks, excessively consuming the model’s attention budget. Second, the long-range decay inherent in Rotary Position Embedding (RoPE) leads to semantic blind spots, preventing these anchors from uniformly perceiving the entire visual input. Accordingly, our objective is to moderately alleviate the attention sink effect on semantic anchors while enhancing their ability to aggregate global visual information, thereby eliminating semantic blind spots. To this end, we propose Extrinsic Distance-Aware Regularization (EDAR), a training-free decoding strategy that augments the attention key space with a static, distance-aware matrix. This matrix jointly redistributes excessive attention away from anchors and injects absolute positional bias to ensure uniform visual coverage. Experiments on LLaDA-V demonstrate that EDAR effectively eliminates semantic blind spots and achieves state-of-the-art performance on both hallucination-specific and general multimodal benchmarks.

ZhaoYang Han, Qihan Lin, Hao Liang, Bowen Chen, Zhou Liu, Wentao Zhang

We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in three key areas: \textbf{a) Long-Duration, Human-Centric Videos:} We carefully selected approximately 1,000 videos from open-source datasets FineVideo based on duration limit and multi-modal information density, focusing on content like lectures, interviews, and vlogs, which contain rich human-centric semantic and contextual attributes. \textbf{b) Diverse and Challenging Task Scenarios:} We have designed six challenging task scenarios, including both Intra-Event and Inter-Event Tasks. \textbf{c) Rigorous and Comprehensive Quality Assurance Pipelines:} We have developed a three-step, semi-automated data quality assurance pipeline to ensure the difficulty and validity of the synthesized questions and answer options. Based on LongInsightBench, we designed a series of experiments. which shows that Omni-modal models(OLMs) still face challenge in tasks requiring precise temporal localization (T-Loc) and long-range causal inference (CE-Caus). Surprisingly, extended experiments reveal the information loss in modal fusion of OLMs, which we called the \textbf{Fusion Deficit Paradox}.

Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun 等

While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This paper takes the first step to investigate whether ALLMs inadvertently leak user privacy solely through acoustic voiceprints and introduces \textit{HearSay}, a comprehensive benchmark constructed from over 22,000 real-world audio clips. To ensure data quality, the benchmark is meticulously curated through a rigorous pipeline involving automated profiling and human verification, guaranteeing that all privacy labels are grounded in factual records. Extensive experiments on \textit{HearSay} yield three critical findings:\textbf{Significant Privacy Leakage}: ALLMs inherently extract private attributes from voiceprints, reaching 92.89% accuracy on gender and effectively profiling social attributes.\textbf{Insufficient Safety Mechanisms}: Alarmingly, existing safeguards are severely inadequate; most models fail to refuse privacy-intruding requests, exhibiting near-zero refusal rates for physiological traits.\textbf{Reasoning Amplifies Risk}: Chain-of-Thought (CoT) reasoning exacerbates privacy risks in capable models by uncovering deeper acoustic correlations.These findings expose critical vulnerabilities in ALLMs, underscoring the urgent need for targeted privacy alignment.The codes and dataset are available at https://github.com/JinWang79/HearSay_Benchmark

Kyungho Lim, Byung-Hoon Kim

Psychiatric narratives encode patient identity not only through explicit identifiers but also through idiosyncratic life events embedded in clinical structure. Existing de-identification approaches, including PHI masking and LLM-based synthetic rewriting, operate at the text level and offer limited control over which semantic elements are preserved or altered. We introduce Anonpsy, a de-identification framework that reformulates the task as graph-guided semantic rewriting. Anonpsy (1) converts each narrative into a semantic graph encoding clinical entities, temporal anchors, and typed relations; (2) applies graph-constrained perturbations that modify identifying context while preserving clinical structure; and (3) regenerates text via graph-conditioned LLM generation. Evaluated on 90 clinician-authored psychiatric case narratives, Anonpsy preserves diagnostic fidelity while achieving consistently low re-identification risk under expert, semantic, and GPT-5-based evaluations. Compared with a strong LLM-only rewriting baseline, Anonpsy yields substantially lower semantic similarity and identifiability. These results demonstrate that explicit structural representations combined with constrained generation provide an effective approach to de-identification for psychiatric narratives.

Kewei Guo, Lingyun Sun, Manhao Guan

Large Language Models (LLMs) exhibit impressive linguistic fluency, yet it remains unclear whether they possess human-like Theory of Mind (ToM) or merely rely on statistical heuristics, particularly in complex social tasks such as irony comprehension. To address the limitations of existing binary benchmarks, this study establishes a multi-dimensional evaluation framework comprising 140 carefully designed probes. These probes are derived from 10 story prototypes based on established cognitive theories. The framework systematically modulates contextual contrast, linguistic cues, and cognitive mechanisms. By comparing the performance of ten state-of-the-art LLMs against 300 human participants, this study uncovers a significant dichotomy in performance. Although LLMs demonstrate superior sensitivity in subsidiary pragmatic inferences, human participants outperform them in holistic irony judgment. Crucially, the results reveal a systematic "intent-irony decoupling", wherein LLMs fail to integrate pragmatic signals into their final judgments. These models exhibit aggressive decision biases and rely on "context-utterance conflict" heuristics. These findings suggest that current LLMs simulate irony comprehension without the underlying cognitive mechanisms. The development of future artificial intelligence may require the integration of explicit ToM modules to bridge the gap between surface-level pattern matching and genuine social understanding.

Jungyang Park, Suho Kang, Jaewoo Park, Jae Hong Kim, Jaewoo Shin, Seonjoon Park, Youngjae Yu

Knowledge Tracing (KT) aims to model student’s knowledge state and predict future performance to enable personalized learning in Intelligent Tutoring Systems. However, traditional KT methods face fundamental limitations in explainability, as they rely solely on the response correctness, neglecting the rich information embedded in students’ problem-solving processes. To address this gap, we propose Knowledge Tracing Leveraging Problem-Solving Process (KT-PSP), which incorporates students’ problem-solving processes to capture the multidimensional aspects of mathematical proficiency. We also introduce KT-PSP-25, a new dataset specifically designed for KT-PSP. Building on this, we present StatusKT, a KT framework that employs a teacher-student-teacher three-stage LLM pipeline to extract students’ Mathematical Proficiency (MP) as intermediate representation. In this pipeline, the teacher LLM first extracts problem-specific proficiency indicators, then a student LLM generates responses based on the student’s solution process, and a teacher LLM evaluates these responses to determine mastery of each indicator. The experimental results on KT-PSP-25 demonstrate that StatusKT improves the prediction performance of existing KT methods. Moreover, StatusKT provides interpretable explanations for its predictions by explicitly modeling students’ mathematical proficiency. Code is available here.

Chris Xing Tian, Weihao Xie, Zhen Chen, Hui Liu, Zhengyuan Yi, Haoliang Li, Shiqi Wang, Siwei Ma

Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses. Effectively adapting RAG systems to domain-specific settings requires specialized, context-rich training data beyond general-purpose question-answering datasets. Here, we propose RAGen, a scalable and modular data-centric framework for generating domain-grounded question–answer–context (QAC) triples tailored to diverse RAG adaptation strategies. These QAC triples serve as training signals for multiple RAG adaptation approaches; in this work, we demonstrate their use for contrastive fine-tuning of embedding models and supervised fine-tuning of LLMs under retrieved contexts. RAGen generates QAC triples by identifying key concepts within documents, producing diverse questions guided by Bloom’s Taxonomy–inspired principles, and pairing them with precise answers extracted from relevant contexts. Its modular pipeline incorporates semantic chunking, hierarchical concept extraction, multi-chunk retrieval, and curated distractor contexts to encourage robust reasoning. Designed for scalability, RAGen efficiently handles large and evolving document corpora without redundant processing, making it particularly suitable for dynamic domains like enterprise knowledge bases.

Ziming Li, Yu Tian, Tian Lan, Jiang Li, Zehua Duo, Guanglai Gao, Xiangdong Su

While Large Language Models (LLMs) excel at capturing communicative intent, this capability introduces a side effect: Pragmatic Hallucination, where models over-interpret literal contexts to generate non-factual inferences. To quantify this, we introduce the PaCE (Pragmatics-as-Context Evaluation) benchmark, comprising over 3,000 manually verified "context-flip" samples. Evaluations across nine mainstream models reveal a significant Context Sensitivity Gap (CSG), with literal accuracy consistently lagging behind pragmatic reasoning. Attribution analysis indicates that Reinforcement Learning from Human Feedback (RLHF) exacerbates this bias, and neither parameter scaling nor Chain-of-Thought (CoT) fully mitigates it. Crucially, "Strict Prompting" effectively reverses the CSG, demonstrating that the phenomenon stems from behavioral lock-in during training rather than inherent capability deficiencies. Furthermore, error patterns exhibit high systematic correlation across diverse architectures. This study highlights that current alignment paradigms lack precise control over pragmatic boundaries, underscoring the necessity for a "Literal Grounding" mechanism in future safety frameworks.

Zesheng Wei, Mengxiang Li, Zilei Wang, Yang Deng

Personalized Large Language Models (LLMs) facilitate more natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained by limited controllability and high resource demands. Furthermore, their reliance on static personality modeling restricts adaptability across varying situations. To address these limitations, we first demonstrate the existence of situation-dependency and consistent situation-behavior patterns within LLM personalities through a multi-perspective analysis of persona neurons. Building on these insights, we propose IRIS, a training-free, neuron-based Identify–Retrieve–Steer framework for advanced situational personality steering. Our approach comprises situational persona neuron identification, situation-aware neuron retrieval, and similarity-weighted steering. We empirically validate our framework on PersonalityBench and our newly introduced SPBench, a comprehensive situational personality benchmark. Experimental results show that our method surpasses best-performing baselines, demonstrating IRIS’s generalization and robustness to complex, unseen situations and different models architecture.