Recent studies have explored the capabilities of large language models (LLMs) in solving knowledge-intensive mathematical reasoning problems. However, existing benchmarks predominantly involve static theorems that LLMs have encountered during pretraining, failing to assess dynamic knowledge integration. In this work, we introduce TaxReasoning, a novel benchmark designed to evaluate LLMs’ abilities in real-world tax calculation scenarios. These tasks require not only mathematical reasoning and numerical computation, but also the extraction and application of complex, frequently updated tax regulations. Through extensive experiments with state-of-the-art LLMs using diverse prompting strategies and knowledge augmentation techniques, we uncover substantial limitations in their ability to handle dynamic, knowledge-intensive questions—primarily due to missing domain-specific knowledge and ineffective retrieval. Even the best-performing models fall significantly short of human-level performance. Our analysis points to key avenues for improvement, including enhancing LLMs' reasoning capabilities, developing more effective knowledge summarization techniques, and improving retrieval strategies. TaxReasoning offers a critical testbed for advancing LLMs in dynamic knowledge-intensive domains.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full retraining or additional clean models. To address these challenges, we propose DUP (Detection-guided Unlearning for Purification), a unified framework that integrates backdoor detection with unlearning-based purification. The detector captures feature-level anomalies by jointly leveraging class-agnostic distances and inter-layer transitions. These deviations are integrated through a weighted scheme to identify poisoned inputs, enabling more fine-grained analysis. Based on the detection results, we purify the model through a parameter-efficient unlearning mechanism that avoids full retraining and does not require any external clean model. Specifically, we innovatively repurpose knowledge distillation to guide the student model toward increasing its output divergence from the teacher on detected poisoned samples, effectively forcing it to unlearn the backdoor behavior. Extensive experiments across diverse attack methods and language model architectures demonstrate that DUP achieves superior defense performance in detection accuracy and purification efficacy.
AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment
PDF ↗Mental health assessment is crucial for early intervention and effective treatment, yet traditional clinician-based approaches are limited by the shortage of qualified professionals. Recent advances in artificial intelligence have sparked growing interest in automated psychological assessment, yet most existing approaches are constrained by their reliance on static text analysis, limiting their ability to capture deeper and more informative insights that emerge through dynamic interaction and iterative questioning. Therefore, in this paper, we propose a multi-agent framework for mental health evaluation that simulates clinical doctor-patient dialogues, with specialized agents assigned to questioning, adequacy evaluation, scoring, and updating. In detail, we introduce an adaptive questioning mechanism in which an evaluation agent assesses the adequacy of user responses to determine the necessity of generating targeted follow-up queries to address ambiguity and missing information. Additionally, we employ a tree-structured memory in which the root node encodes the user's basic information, while child nodes (e.g., topic and statement) organize key information according to distinct symptom categories and interaction turns. This memory is dynamically updated throughout the interaction to reduce redundant questioning and enhance the information extraction and contextual tracking capabilities. Experimental results on the DAIC-WOZ dataset illustrate the effectiveness of our proposed method, which achieves better performance than existing approaches. Our code is released at \url{https://github.com/MindIntLab-HFUT/AgentMental}.
End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering
PDF ↗Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented generation, a speech-related retriever shows promising in help preprocessing long-form speech. But the performance of existing speech-related retrievers is lacking. To address this challenge, we propose CLSR, an end-to-end contrastive language-speech retriever that efficiently extracts question-relevant segments from long audio recordings for downstream SQA task. Unlike conventional speech-text contrastive models, CLSR incorporates an intermediate step that converts acoustic features into text-like representations prior to alignment, thereby more effectively bridging the gap between modalities. Experimental results across four cross-modal retrieval datasets demonstrate that CLSR surpasses both end-to-end speech related retrievers and pipeline approaches combining speech recognition with text retrieval, providing a robust foundation for advancing practical long-form SQA applications.
Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation
PDF ↗Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.
Recent studies have raised significant concerns regarding the reliability of current mathematical benchmarks, highlighting key limitations such as simplistic design and potential data contamination that undermine evaluation accuracy. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we develop question-generating functions to produce random variable questions (RVQs), whose background content mirrors the original benchmark problems, but with randomized variable combinations, rendering them "unseen" to LLMs. Models must completely understand the inherent question pattern to correctly answer RVQs with diverse variable combinations. Thus, an LLMs' genuine reasoning capability is reflected through its accuracy and robustness on RV-Bench. We conducted extensive experiments on over 30 representative LLMs across more than 1,000 RVQs. Our findings reveal that LLMs exhibit a proficiency imbalance between encountered and "unseen" data distributions. Furthermore, RV-Bench reveals that proficiency generalization across similar mathematical reasoning tasks is limited, but we verified that it can still be effectively elicited through test-time scaling.
Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts
PDF ↗With the growing number of submitted scientific papers, there is an increasing demand for systems that can assist reviewers in evaluating research claims. Experimental results are a core component of scientific work, often presented in varying formats such as tables or charts. Understanding how robust current multimodal large language models (multimodal LLMs) are at verifying scientific claims across different evidence formats remains an important and underexplored challenge. In this paper, we design and conduct a series of experiments to assess the ability of multimodal LLMs to verify scientific claims using both tables and charts as evidence. To enable this evaluation, we adapt two existing datasets of scientific papers by incorporating annotations and structures necessary for a multimodal claim verification task. Using this adapted dataset, we evaluate 12 multimodal LLMs and find that current models perform better with table-based evidence while struggling with chart-based evidence. We further conduct human evaluations and observe that humans maintain strong performance across both formats, unlike the models. Our analysis also reveals that smaller multimodal LLMs (under 8B) show weak correlation in performance between table-based and chart-based tasks, indicating limited cross-modal generalization. These findings highlight a critical gap in current models' multimodal reasoning capabilities. We suggest that future multimodal LLMs should place greater emphasis on improving chart understanding to better support scientific claim verification.
REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation
PDF ↗Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant challenge of balancing translation quality and latency. We introduce a strategy to optimize this tradeoff: wait for more input only if you gain information by doing so. Based on this strategy, we present Regularized Entropy INformation Adaptation (REINA), a novel loss to train an adaptive policy using an existing non-streaming translation model. We derive REINA from information theory principles and show that REINA helps push the reported Pareto frontier of the latency/quality tradeoff over prior works. Utilizing REINA, we train a SimulST model on French, Spanish and German, both from and into English. Training on only open source or synthetically generated data, we achieve state-of-the-art (SOTA) streaming results for models of comparable size. We also introduce a metric for streaming efficiency, quantitatively showing REINA improves the latency/quality trade-off by as much as 21 percent compared to prior approaches, normalized against non-streaming baseline BLEU scores.
Large language models have demonstrated remarkable capabilities across many tasks, yet face significant challenges when dealing with recursive reasoning problems—those requiring the resolution of nested hierarchical structures. While prior research has extensively studied length generalization (a model’s ability to handle longer sequences than seen during training), we investigate a distinct and underexplored limitation: depth generalization. Here, depth refers to the number of nested levels in a hierarchical problem, such as the layers of parentheses in a mathematical expression or the nesting of logical clauses in a Boolean formula. Our work reveals that standard transformer architectures struggle with problems involving deeper recursion than encountered during training, even when they perform well on longer but non-nested sequences. This limitation stems from their inability to maintain stack-like behavior—the capacity to track and resolve multiple levels of nested dependencies. Through systematic analysis, we demonstrate how this architectural constraint leads to rapid performance decay as the depth of recursion increases. To address this challenge, we develop a novel looped locate-and-replace pipeline that decomposes recursive problems into manageable subcomponents. The approach employs two specialized models: a locator that identifies solvable subexpressions and a replacer that evaluates these components while preserving the overall structure. We evaluate this method in three carefully designed domains—Boolean algebra, recursive arithmetic, and propositional logic—each with a controllable depth of recursion. Our results show that the proposed method effectively alleviates performance decay when tested on out-of-distribution recursion depth.
FinMathBench: A Formula-Driven Benchmark for Evaluating LLMs’ Math Reasoning Capabilities in Finance
PDF ↗Many existing financial math reasoning benchmarks suffer from data contamination and high manual construction costs. To address this, we propose a novel formula-driven approach to dynamically construct math reasoning benchmarks in finance. Our two-stage approach: (1) generates single-formula questions by LLMs using a "Mask-for-Solve" paradigm for ground truth answers, and (2) synthesizes multi-formula questions through hierarchical tree-based DAGs. Our approach ensures novelty (via LLMs' creativity) and controllability of difficulty (via DAG structure). Based on a self-constructed financial formula bank, we utilize the proposed method to build FinMathBench, the first formula-driven and fully LLM-generated benchmark aimed at assessing LLMs' math reasoning abilities in finance, containing 946 questions across 4 complexity levels. Evaluation results on 40 LLMs demonstrate significant accuracy drops in multi-formula questions, e.g., 72.9% (1-Formula) to 14.0% (4-Formula) for GPT-4o under Chain-of-Thought prompting. Three critical flaws of LLMs are also observed: poor direct calculation performance, bias toward frequently solved variables in formulas, and erroneous "correction" of valid but extreme financial values. These findings highlight gaps in current LLMs' domain-specific reasoning and underscore FinMathBench's value for advancing robust financial LLMs.
Task-specific data selection, which aims to identify the most relevant training instances from a large corpus to optimize performance on a target task, is a critical challenge in modern AI. Prevailing methods typically rely on either representation clustering or gradient-based influence estimation. However, these approaches have notable limitations. Representation-based methods rely on static features; they measure semantic proximity but are agnostic to the process of learning. Conversely, influence-based methods, while capturing optimization directions, often focus narrowly on aligning with the validation loss, which may not fully correlate with the desired capabilities. To address these issues, we propose TRACE, a novel algorithm that simultaneously considers data consistency in the optimization direction and representation space, and performs TRajectory-based Activation Change Estimation to select instruction. Specifically, TRACE first performs a targeted weight update using the validation set. It then captures the optimization trajectory by calculating the change in neuron activations for each before and after this update. By selecting data whose activation change are most similar to those of the validation set, TRACE ensures alignment in both the representational and optimization domains. Our experiments demonstrate that TRACE outperforms baseline methods across various tasks, particularly in complex, data-scarce scenarios.
ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions
PDF ↗Instruction-following is a critical capability of Large Language Models (LLMs). While existing works primarily focus on assessing how well LLMs adhere to user instructions, they often overlook scenarios where instructions contain conflicting constraints—a common occurrence in complex prompts. The behavior of LLMs under such conditions remains under-explored. To bridge this gap, we introduce ConInstruct, a benchmark specifically designed to assess LLMs' ability to detect and resolve conflicts within user instructions. Using this dataset, we evaluate LLMs' conflict detection performance and analyze their conflict resolution behavior. Our experiments reveal two key findings: (1) Most proprietary LLMs exhibit strong conflict detection capabilities, whereas among open-source models, only DeepSeek-R1 demonstrates similarly strong performance. DeepSeek-R1 and Claude-4.5-Sonnet achieve the highest average F1-scores at 91.5% and 87.3%, respectively, ranking first and second overall. (2) Despite their strong conflict detection abilities, LLMs rarely explicitly notify users about the conflicts or request clarification when faced with conflicting constraints. These results underscore a critical shortcoming in current LLMs and highlight an important area for future improvement when designing instruction-following LLMs.
PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis
PDF ↗Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit modality competition: dominant modalities tend to overshadow weaker ones, leading to suboptimal performance. In this paper, we propose PaSE, a novel Prototype-aligned Calibration and Shapley-optimized Equilibrium framework, which enhances collaboration while explicitly mitigating modality competition. PaSE first applies Prototype-guided Calibration Learning (PCL) to refine unimodal representations and align them through an Entropic Optimal Transport mechanism that ensures semantic consistency. To further stabilize optimization, we introduce a Dual-Phase Optimization strategy. A prototype-gated fusion module is first used to extract shared representations, followed by Shapley-based Gradient Modulation (SGM), which adaptively adjusts gradients according to the contribution of each modality. Extensive experiments on IEMOCAP, MOSI, and MOSEI confirm that PaSE achieves the superior performance and effectively alleviates modality competition.
MentalGuide: Towards Multi-Turn, State-Aware and Strategy-Driven Conversations for Mental Health Support
PDF ↗The global shortage of psychiatrists has become a critical issue, and the advent of large language models (LLMs) presents new opportunities to address this challenge. However, existing approaches continue to underperform in multi-turn mental health counseling, particularly in the arrangement of counseling strategies. To overcome these limitations, we propose MentalGuide, a state-aware and strategy-driven conversation framework designed for multi-turn mental health support. Our method integrates expert-derived prior probabilities of counseling strategies tailored to the target client's state with the reasoning capabilities of LLMs. This enables effective strategy formulation and strategy-driven response generation, without the need for additional training. Experimental results show that MentalGuide surpasses baselines in automated and human expert evaluations, demonstrating the closest alignment with real-world multi-turn counseling dynamics.
State-of-the-art (SOTA) fact-checking systems combat misinformation by employing autonomous LLM-based agents to decompose complex claims into smaller sub-claims, verify each sub-claim individually, and aggregate the partial results to produce verdicts with justifications (explanations for the verdicts). The security of these systems is crucial, as compromised fact-checkers can amplify misinformation, but remains largely underexplored. To bridge this gap, this work introduces a novel threat model against such fact-checking systems and presents Fact2Fiction, the first poisoning attack framework targeting SOTA agentic fact-checking systems. Fact2Fiction employs LLMs to mimic the decomposition strategy and exploit system-generated justifications to craft tailored malicious evidences that compromise sub-claim verification. Extensive experiments demonstrate that Fact2Fiction achieves 8.9%-21.2% higher attack success rates than SOTA attacks across various poisoning budgets and exposes security weaknesses in existing fact-checking systems, highlighting the need for defensive countermeasures.
Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting. We propose a comprehensive locality evaluation framework, covering three key dimensions: random-image locality, no-image locality, and consistent-image locality, operationalized through seven distinct data types, enabling a detailed and structured analysis of multimodal edits. We introduce De-VQA, a dynamic evaluation for visual question answering, uncovering a phenomenon we term transient blindness, overfitting to edit-similar text while ignoring visuals. Token analysis shows edits disproportionately affect textual tokens. We propose locality-aware adversarial losses to balance cross-modal representations. Empirical results demonstrate that our approach consistently outperforms existing baselines, reducing transient blindness and improving locality by 17% on average.
Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning
PDF ↗Large language models have demonstrated remarkable capabilities in complex mathematical reasoning tasks, but they inevitably generate errors throughout multi-step solutions. Process-level Reward Models (PRMs) have shown great promise by providing supervision and evaluation at each intermediate step, thereby effectively improving the models’ reasoning abilities. However, training effective PRMs requires high-quality process reward data, yet existing methods for constructing such data are often labour-intensive or inefficient. In this paper, we propose an uncertainty-driven framework for automated process reward data construction, encompassing both data generation and annotation processes for PRMs. Additionally, we identify the limitations of both majority vote and PRMs, and introduce two generic uncertainty-aware output aggregation methods: Hybrid Majority Reward Vote and Weighted Reward Frequency Vote, which combine the strengths of majority vote with PRMs. Extensive experiments on ProcessBench, MATH, and GSMPlus show the effectiveness and efficiency of the proposed PRM data construction framework, and demonstrate that the two output aggregation methods further improve the mathematical reasoning abilities across diverse PRMs.
Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment
PDF ↗Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods.
LaTeX2Layout: High-Fidelity, Scalable Document Layout Annotation Pipeline for Layout Detection
PDF ↗General-purpose Vision-Language Models (VLMs) are increasingly integral to modern AI systems for document understanding, yet their ability to perform fine-grained layout analysis remains severely underdeveloped. Overcoming this limitation requires large-scale, high-fidelity training datasets. However, current annotation methods that rely on parsing rendered PDFs are costly, error-prone, and difficult to scale. We propose a different paradigm: extracting ground-truth layout directly from the LaTeX compilation process rather than the final PDF. We present LaTeX2Layout, a generalizable procedural pipeline that recovers pixel-accurate bounding boxes and reading order from compiler traces. This enables the generation of a 140K-page dataset, including 120K programmatically generated synthetic variants that more than double the layout diversity of real-world data. Using this dataset, we fine-tune an efficient 3B-parameter VLM with an easy-to-hard curriculum that accelerates convergence. Our model achieves Kendall's tau=0.95 for reading order and mAP@50=0.91 for element grounding, delivering nearly 200% relative improvement over strong zero-shot baselines such as GPT-4o and Claude-3.7.
Deploying language models often requires navigating accuracy vs. performance trade-offs to meet latency constraints while preserving utility. Traditional model distillation reduces size but incurs substantial costs through training separate models. We introduce ModularStarEncoder (MoSE), a 1-billion-parameter multi-exit encoder for code retrieval and classification that employs a novel Self-Distillation mechanism. This approach significantly enhances lower-layer representations, enabling flexible deployment of different model portions with favorable performance trade-offs. Our architecture improves text-to-code and code-to-code search by targeting specific encoder layers as exit heads, where higher layers guide earlier ones during training, thereby improving intermediate representations at minimal additional cost. We further enhance MoSE with a repository-level contextual loss that maximizes training context window utilization. Additionally, we release a new dataset created through code translation that extends text-to code benchmarks with cross-language code-to-code pairs. Evaluations demonstrate the effectiveness of Self-Distillation as a principled approach to trading inference cost for accuracy across various code understanding tasks.