The rapid spread of fake news threatens social stability and public trust, highlighting the urgent need for its effective detection.Although large language models (LLMs) show potential in fake news detection, they are limited by knowledge cutoff and easily generate factual hallucinations when handling time-sensitive news.Furthermore, the thinking of a single LLM easily falls into early stance locking and confirmation bias, making it hard to handle both content reasoning and fact checking simultaneously.To address these challenges, we propose ZoFia, a two-stage zero-shot fake news detection framework.In the first retrieval stage, we propose novel Hierarchical Salience and Salience-Calibrated Minimum Marginal Relevance (SC-MMR) algorithm to extract core entities accurately, which drive dual-source retrieval to overcome knowledge and evidence gaps.In the subsequent stage, a multi-agent system conducts multi-perspective reasoning and verification in parallel and achieves an explainable and robust result via adversarial debate.Comprehensive experiments on two public datasets show that ZoFia outperforms existing zero-shot baselines and even most few-shot methods.Our code has been open-sourced to facilitate the research community at https://github.com/SakiRinn/ZoFia.
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
Large language models (LLMs) increasingly act as tool-using agents, and existing methods for evaluating and optimizing tool usage by LLMs typically assume a static tool environment with fixed APIs and documentation. In practice, toolsets evolve as tools are added, changed, or deprecated, introducing instability for agents that must retain prior competence while adapting to new capabilities. We formalize this challenge as the stability–adaptation dilemma. To address it, we propose ContDa, a continual documentation adaptation framework that provides a generalizable solution to this problem, enabling LLM agents to self-evolve by updating tool documentation. ContDa combines relation-guided exploration, which leverages functionally related existing tools as anchors to probe and identify new tool capabilities, with relation-aware adjustment that organizes overlapping tools and explicitly encodes usage preferences and fallback options among them. We then introduce complementary metrics that disentangle performance from stability and adaptation. Experiments across three evolution patterns on dynamic extensions of StableToolBench and RestBench show that ContDa consistently improves average performance by enhancing the discovery of new capabilities while incurring only limited loss of previously solved tasks, demonstrating documentation adaptation as an effective and lightweight mechanism for robust tool use in evolving environments. Our code is available at https://github.com/Bingo-W/ContDa.
D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
PDF ↗Supervised Fine-Tuning (SFT) accelerates task-specific large language models (LLMs) development, but the resulting proliferation of fine-tuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single pre-trained LLM with multiple compressed delta weights. However, existing methods fail on models fine-tuned with large-scale datasets. We find that larger SFT data scale amplifies delta parameter magnitude, singular values, and entropy, exacerbating compression errors. To tackle this, we propose D-QRELO ( \textbf{D}elta Compression via \textbf{Q}uantization and \textbf{R}sidual \textbf{Lo}w-Rank), a novel training- and data-free delta compression method. It combines coarse-grained one-bit quantization to capture the dominant structure of the delta, followed by compensated residual low-rank approximation to recover fine-grained details from the smaller residual error. Experiments on various LLMs spanning dense and MoE architectures across multiple domains under this challenging setting demonstrate that D-QRELO outperforms existing methods. Moreover, we establish key design principles for delta compression through extensive empirical analysis, demonstrating how task difficulty, architecture, and layer positioning create predictable patterns that can guide optimal compression strategies in production systems.
Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned and Distribution-Controllable Persona Generation (TAD-PG) and introduce HACHIMI, a multi-agent Propose-Validate-Revise framework that generates theory-aligned, quota-controlled personas. HACHIMI factorizes each persona into a theory-anchored educational schema, enforces developmental and psychological constraints via a neuro-symbolic validator, and combines stratified sampling with semantic deduplication to reduce mode collapse. The resulting HACHIMI-1M corpus comprises 1 million personas for Grades 1-12. Intrinsic evaluation shows near-perfect schema validity, accurate quotas, and substantial diversity, while external evaluation instantiates personas as student agents answering CEPS and PISA 2022 surveys; across 16 cohorts, math and curiosity/growth constructs align strongly between humans and agents, whereas classroom-climate and well-being constructs are only moderately aligned, revealing a fidelity gradient. All personas are generated with Qwen2.5-72B, and HACHIMI provides a standardized synthetic student population for group-level benchmarking and social-science simulations. Resources available at https://github.com/ZeroLoss-Lab/HACHIMI.
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization
PDF ↗Although post-training quantization (PTQ) provides an efficient numerical compression scheme for deploying large language models (LLMs) on resource-constrained devices, the representativeness and universality of calibration data remain a core bottleneck in determining the accuracy of quantization parameters. Traditional PTQ methods typically rely on limited samples, making it difficult to capture the activation distribution during the inference phase, leading to biases in quantization parameters. To address this, we propose **FAQ** (Family-Aware Quantization), a calibration data regeneration framework that leverages prior knowledge from LLMs of the same family to generate high-fidelity calibration samples. Specifically, FAQ first inputs the original calibration samples into a larger LLM from the same family as the target model, regenerating a series of high-fidelity calibration data using a highly consistent knowledge system. Subsequently, this data, carrying Chain-of-Thought reasoning and conforming to the expected activation distribution, undergoes group competition under expert guidance to select the best samples, which are then re-normalized to enhance the effectiveness of standard PTQ. Experiments on multiple model series, including Qwen3-8B, show that FAQ reduces accuracy loss by up to 28.5% compared to the baseline with original calibration data, demonstrating its powerful potential and contribution.
CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments
PDF ↗Services powered by large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises serious privacy concerns. Trusted Execution Environments (TEEs) provide a secure computation environment, enabling sensitive inputs to be safely processed. However, directly deploying high-capacity LLMs in TEEs is often prohibitively expensive due to computation and memory constraints. To reconcile privacy, efficiency, and generation quality, we propose CoTrust, a privacy-preserving collaborative inference framework that combines LLMs with small language models (SLMs) inside TEE. CoTrust uses multiple de-identified views to let the LLM produce a consensus scaffold capturing answer reasoning without exposing private information, which the SLM then grounds in the full input to generate the final response. Experiments on multiple question answering and summarization benchmarks show that CoTrust approaches the performance of unconstrained LLMs, outperforms existing privacy-preserving baselines, and maintains strong privacy protection, while remaining efficient in a TDX-based TEE implementation.
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
PDF ↗Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack paradigms: "Gradient Interference." This phenomenon represents an optimization failure triggered by conflicting strategies during end-to-end training. To resolve this, we propose an Adaptive Threat-Aware Adversarial Tuning (ATAAT) framework. Through its core "Threat-Method Adaptive Mapping" mechanism, ATAAT intelligently selects the optimal gradient decoupling strategy based on the adversary’s capabilities. Extensive experiments demonstrate that ATAAT exhibits significant advantages, achieving a highly robust Targeted Attack Success Rate (TASR > 80%) while maintaining extreme stealthiness with merely a 5% poisoning rate. It efficiently handles complex semantic-level triggers and achieves implicit decoupled attacks in data poisoning scenarios for the first time. This work reveals a critical security vulnerability in VLAs and provides theoretical and methodological support for future defense architectures.
Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommenders instead leverage natural-language representations that are easier to interpret and integrate with downstream reasoning modules. This paper studies how to construct effective textual profiles for users and items, and how to align them for recommendation.A central difficulty is that the best profile format is not known a priori: manually designed templates can be brittle and misaligned with task objectives. Moreover, generating user and item profiles independently may produce descriptions that are individually plausible yet semantically inconsistent for a specific user–item pair. We propose Duet, an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. Duet follows a three-stage procedure: it first turns raw histories and metadata into compact cues, then expands these cues into paired profile prompts and then generate profiles, and finally optimizes the generation policy with reinforcement learning using downstream recommendation performance as feedback. Experiments on three real-world datasets show that Duet consistently outperforms strong baselines, demonstrating the benefits of template-free profile exploration and joint user–item textual alignment. Project page: https://duet-rec.github.io/.
Multimodal Named Entity Recognition relies on visual context to resolve textual ambiguities. To mitigate data scarcity, Data Augmentation (DA) has become a standard practice; however, existing methods predominantly adopt a one-size-fits-all and random perturbation paradigm, ignoring the internal state of the target model. In this paper, we first conduct a quantitative analysis, revealing that a significant portion of errors (over 30%) are model-specific, stemming from the unique biases of different architectures. To address this, we propose Memory-Guided Hard Data Augmentation, a framework designed to systematically repair these specific defects. First, we employ K-fold cross-validation to identify model-specific Hard Data. Second, we construct a Memory Tree and utilize Large Language Models (LLMs) with a clustering mechanism to induce macro-level error patterns from micro-level failures. This facilitates a paradigm shift from stateless instance-driven augmentation to a logical pattern-driven approach. Finally, we introduce an iterative augmentation mechanism that triggers recursive generation for stubborn instances that fail initial quality filters. Extensive experiments on Twitter-2015 and Twitter-2017 benchmarks demonstrate that our framework consistently yields significant performance gains across various MNER backbones.
TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
PDF ↗Detecting toxic content using language models is crucial yet challenging. While substantial progress has been made in English, toxicity detection in French remains underdeveloped, primarily due to the lack of culturally relevant, human-annotated, large-scale datasets. In this work, we release TOXIFRENCH, a dataset of 53,622 French online comments, together with a 1,388-sample balanced benchmark split for systematic evaluation. The dataset is constructed via a semi-automated annotation pipeline that reduces manual labeling to only 10% through high-confidence LLM-based pre-annotation and human verification, while ensuring statistically near-perfect alignment with human-only annotation. We then benchmark a broad range of models and uncover a counterintuitive insight: Small Language Models (SLMs) often surpass larger models in robustness and generalization on this task. Motivated by this finding, we propose a novel Chain-of-Thought (CoT) fine-tuning strategy using a dynamic weighted loss that progressively emphasizes the model’s final decision, significantly improving faithfulness. Our fine-tuned 4B model (Qwen3-4B) achieves state-of-the-art performance on the benchmark, improving its balanced accuracy by 10% over its baseline and achieving better performance than GPT-4o and DeepSeek-R1 on our benchmark, while successfully retaining cross-lingual capabilities.
Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token complexity when processing long contexts. However, these recurrent models struggle with tasks that require accurate recall of contextual information from long contexts, because all contextual information is compressed into a fixed-size recurrent state. Previous studies have shown that recall ability is positively correlated with the recurrent state size, yet directly training RNNs with large recurrent states results in high training costs. In this paper, we introduce StateX, a post-training framework that efficiently expands the states of pre-trained RNNs. For two popular classes of RNNs, linear attention and state-space models, we design post-training architectural modifications in StateX, to scale up the state size with no or negligible increase in model parameters. Experiments on models with up to 1.3B parameters demonstrate that StateX efficiently enhances the recall and in-context learning performance of RNNs without incurring high post-training costs or compromising other capabilities.
ToMELP: A Theory-of-Mind Benchmark for Route-Controlled Persuasion under the Elaboration Likelihood Model
PDF ↗Theory of Mind (ToM) is widely regarded as central to effective persuasion, yet existing evaluations often fail to capture the infer–apply loop that arises in real-world dialogue. We introduce Theory-of-Mind-Guided Elaboration-Likelihood Persuasion (ToMELP), a benchmark that jointly conditions on the audience persona p and the Elaboration Likelihood Model (ELM) route r \in \{\text{central}, \text{peripheral}\} within persuasive conversations. The benchmark tests whether large language models can perform ToM inference over multi-turn interactions and leverage these inferences for controllable persuasive generation. ToMELP provides a structured interface with evidence annotations, enabling automated evaluation of persuasive effectiveness, route alignment/deviation, evidence quality under the central route, and robustness to perturbations.
Multi-agent systems utilizing large language models often assign authoritative roles to improve performance, yet the impact of authority bias on agent interactions remains underexplored. We present the first systematic analysis of role-based authority bias in free-form multi-agent evaluation using ChatEval. Applying French and Raven’s power-based theory, we classify authoritative roles into legitimate, referent, and expert types and analyze their influence across 12-turn conversations. Experiments with GPT-4o and DeepSeek R1 reveal that Expert and Referent power roles exert stronger influence than Legitimate power roles. Crucially, authority bias emerges not through active conformity by general agents, but through authoritative roles consistently maintaining their positions while general agents demonstrate flexibility. Furthermore, authority influence requires clear position statements, as neutral responses fail to generate bias. These findings provide key insights for designing multi-agent frameworks with asymmetric interaction patterns.
While LLMs enable personalized chatbots, their effectiveness in child-centered personalization remains unclear, as systematic evaluation of child-specific preferences is still lacking. To address this gap, we introduce ChildEval, a benchmark for evaluating LLMs’ ability to infer and follow child-centered preferences in long-context conversations. ChildEval contains 29K synthesized persona profiles of children aged 3–6, providing relatively static background information. Each persona is associated with a child preference—which may align with, conflict with, or be independent of the persona—expressed either explicitly in a single sentence or implicitly through 6–10 turn dialogues. Explicit and implicit preferences are designed to reflect the same underlying preference but differ in expression, capturing dynamic aspects of preference expression rather than changes in the static persona. The benchmark spans five top-level and fourteen sub-level categories covering children’s daily lives and development. We further propose fine-grained, child-centric evaluation protocols to systematically assess open-source LLMs. Experimental results demonstrate how different personalized representations affect LLM responses and suggest that finetuning on ChildEval can enhance child-centered performance. Our code and dataset are available at https://github.com/ziyanluo/ChildEval.
Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process. While existing approaches attempt to mitigate this by relying on external tools or task decomposition, they fail to enhance the model’s intrinsic constraint awareness. To address this, we propose Constraint-Aware Reinforcement Learning (CARL), a novel RL framework designed to strengthen LLMs’ intrinsic focus on constraints. CARL introduces a constraint-aware reward by comparing the model’s output distributions under constrained and unconstrained inputs, encouraging constraint focus and penalizing neglect.Compatible with various RL frameworks and requiring no external solvers or top models, CARL enables scalable, end-to-end constraint-aware planning. Extensive experiments on BlocksWorld, TravelPlanner, and T-Eval demonstrate that CARL significantly outperforms standard Reinforcement Fine-Tuning (RFT) baselines and state-of-the-art reasoning models, exhibiting a markedly increased focus on constraints.
CogBench: Benchmarking Cognitive Alignment of Large Language Models in Educational Question Answering
PDF ↗Large language models (LLMs) possess strong capabilities in language understanding and generation, as well as remarkable problem-solving abilities. In the educational domain, a representative application is to employ LLMs as learning assistants that answer students’ questions and support their learning processes. In such scenarios, it is crucial for the model to perceive a student’s cognitive level and provide explanations that are appropriate to that level. However, whether LLMs can effectively accomplish this task has not yet been thoroughly investigated. To address this gap, we introduce CogBench, an evaluation benchmark designed to assess the cognitive alignment capabilities of LLMs in educational QA. CogBench comprises 2.1K mathematics questions, each associated with multiple valid solutions that rely on knowledge and reasoning at different cognitive levels. Building on this structure, we formulate three cognition-aware evaluation tasks and propose three complementary metrics to quantify cognitive alignment from multiple perspectives. Extensive experiments on 11 representative LLMs reveal that, while models can often produce correct answers, they still struggle to consistently generate explanations that are aligned with the intended cognitive level. These results highlight substantial room for improvement and establish CogBench as a diagnostic benchmark for advancing cognitively aligned educational AI systems.
Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science. To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.
Retrieval-Augmented Generation (RAG) enhances the factual accuracy of Large Language Model (LLM) outputs based on external knowledge bases. These knowledge bases often carry significant intellectual property (IP) value, raising the urgent need for robust watermarking techniques to protect IP. However, existing RAG watermarking methods remain in their infancy, facing challenges such as limited encoding capacity and potential degradation of RAG performance or knowledge quality. In this paper, we propose knowledge-infused and multi-bit watermarking (KMW) for RAG knowledge bases. It generates watermark text to infuse the knowledge base by benign knowledge completion and a tailored generative watermarking algorithm. Each generated text can carry a multi-bit watermark segment. For effective detection, we design a Watermark Text Indexer that optimizes queries for steady retrieval of watermarked texts. Experiments on multiple datasets and LLMs show KMW reliably extracts watermarks from adversarial RAGs. It is robust against knowledge selection, alteration, expansion, and RAG setting restrictions, while remaining stealthy and secure. This highlights that KMW ensures effective IP protection for RAG systems. Our code is available here https://github.com/iieSKLCSDsg/KMW.
Speculative decoding (SPD) has emerged as a promising technique to accelerate Large Language Model (LLM) inference. However, current approaches typically enforce a uniform verification standard, neglecting the inherent heterogeneity of natural language and failing to distinguish between semantically-rich content and structurally-predictable syntax. In this paper, we propose LinguaSpec, a training-free framework that leverages linguistic priors to enable adaptive drafting and verification. Specifically, we introduce: (1) a Static Linguistic Probe (SLP) to categorize tokens with zero latency; (2) Syntactic Normalized Surprisal (SNS) to calibrate uncertainty against category-specific entropy; and (3) a dual strategy of Syntactically-Guided Elastic Expansion and POS-Adaptive Deferred Verification to dynamically adjust drafting depth and verification rigor. By balancing semantic integrity with structural efficiency, LinguaSpec significantly accelerates inference without requiring additional training. Experimental results demonstrate its superior performance across diverse benchmarks.
Long chain-of-thought (CoT) reasoning improves the performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps. We suggest that hallucination in long CoT reasoning is better understood as an evolving latent state rather than a one-off erroneous event. Accordingly, we treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level hallucination signal that tracks the global evolution of the reasoning state over the entire trajectory. Overall, our approach enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence.