Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter-editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model’s original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to the critic phase—the evaluation of whether generated formalizations truly capture the semantic intent of the original problem. In this paper, we introduce CriticLean, a novel critic-guided reinforcement learning framework that elevates the role of the critic from a passive validator to an active learning component. Specifically, first, we propose the CriticLeanGPT, trained via supervised fine-tuning and reinforcement learning, to rigorously assess the semantic fidelity of Lean 4 formalizations. Then, we introduce CriticLeanBench, a benchmark designed to measure models’ ability to distinguish semantically correct from incorrect formalizations, and demonstrate that our trained CriticLeanGPT models can significantly outperform strong open- and closed-source baselines. Building on the CriticLean framework, we construct FineLeanCorpus, a dataset comprising over 509K problems that exhibits rich domain diversity, broad difficulty coverage, and high correctness based on human evaluation.Overall, our findings highlight that optimizing the critic phase is essential for producing reliable formalizations and we hope our CriticLean will provide valuable insights for future advances in formal mathematical reasoning.
HOPE: Hybrid Optimized Parallel Encoding with Supervised and Unsupervised Semantic Fusion for Depression Symptom Detection
PDF ↗Timely detection of depression symptoms is essential for early intervention, and the continuous stream of user-generated content on social media provides an ideal source for this purpose. To address this challenge, we propose HOPE, a Hybrid Optimized Parallel Encoding framework that combines supervised symptom relevance signals with unsupervised intrinsic semantic clustering. This parallel design enables robust symptom detection under limited labeled data and introduces a distinctive semantic-similarity perspective with automatic class-anchor adjustment. We also propose an optimized hybrid semantic fusion mechanism to combine supervised and unsupervised scores through a learnable module. We evaluate our system on multiple benchmark datasets and surpass previous approaches, demonstrating its effectiveness in detecting fine-grained symptoms and early warning of mental health risk. Source code is available at https://github.com/candleMind/hope.
RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis
PDF ↗Recent advances in speech large language models (e.g., GPT-4o) have enabled end-to-end spoken interactions, yet their robustness in real-world applications remains unclear, where systems must assist users in completing specific tasks under complex conditions such as multi-turn, ambiguous, and often spontaneous speech, as well as natural alternation between speech and text. Task-oriented dialogue (TOD) offers a realistic scenario to evaluate whether models can effectively help users accomplish such task-oriented goals, but existing benchmarks are mainly text-based, and the few speech datasets are limited to English and often neglect spontaneous disfluencies and speaker diversity. To address this gap, we introduce RealTalk-CN, the first Chinese multi-turn, multi-domain speech–text TOD dataset, containing 5.4k dialogues (60K turns, ~150 hours) of real human-to-human recordings with detailed annotations for dialogue states, disfluency types, and speaker characteristics. Based on this dataset, we propose a cross-modal interaction task supporting dynamic speech-text switching and a comprehensive evaluation protocol assessing robustness to disfluencies, sensitivity to speaker variation, and cross-domain generalization. Experiments on state-of-the-art models demonstrate the challenges posed by RealTalk-CN and establish its value as a benchmark for developing reliable and fair Speech LLMs in real-world deployments. The dataset and evaluation framework are available to encourage further research.
Large language models (LLMs) have demonstrated remarkable progress in reasoning, often through supervised fine-tuning (SFT). However, SFT is resource-intensive, relying on large curated datasets, rejection-sampled demonstrations, and uniform optimization across all tokens—even though only a fraction carry meaningful learning value. In this work, we explore a counterintuitive idea: can smaller language models (SLMs) teach larger language models (LLMs) by revealing high-value reasoning moments that reflect the latter’s unique strength? We propose LightReasoner, a novel framework that leverages the behavioral divergence between a stronger expert model (LLM) and a weaker amateur model (SLM). LightReasoner operates in two stages: (1) a sampling stage that pinpoints critical reasoning moments and constructs supervision examples capturing the expert’s advantage through expert–amateur contrast, and (2) a fine-tuning stage that aligns the expert model with these distilled examples, amplifying its reasoning strengths. Across seven benchmarks, LightReasoner improves accuracy by up to 28.1%, while reducing time consumption by 90%, sampled problems by 80%, and tuned token usage by 99%, all without relying on ground-truth labels. By turning weaker SLMs into effective teaching signals, LightReasoner offers a scalable and resource-efficient approach for advancing LLM reasoning.
Vision-and-language pretraining (VLP) in medicine leverages contrastive learning on image–text pairs, often enhanced with masked modeling. However, existing methods face two challenges: difficulty reconstructing key pathological features due to limited data, and reliance on either paired or image-only datasets without combining both. To address this, we propose **MMCLIP** (**M**asked **M**edical **C**ontrastive **L**anguage–**I**mage **P**re-training), which introduces two modules: **AttMIM**: Masks image features highly correlated with text to improve reconstruction of fine medical details. **EntMLM**: Masks key medical entities in text and reconstructs them using visual cues. Furthermore, **MMCLIP** incorporates unpaired data through disease-kind prompts, achieving state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.
CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
PDF ↗The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agent framework dedicated to generating targeted adversarial test cases that expose latent vulnerabilities in program submissions. Mimicking the hack mechanism in competitive programming, CodeHacker employs a multi-strategy approach—including stress testing, anti-hash attacks, and logic-specific targeting to break specific code submissions. To ensure the validity and reliability of these attacks, we introduce a Calibration Phase, where the agent iteratively refines its own Validator and Checker via self-generated adversarial probes before evaluating contestant code. Experiments demonstrate that CodeHacker significantly improves the True Negative Rate (TNR) of existing datasets, effectively filtering out incorrect solutions that were previously accepted. Furthermore, generated adversarial cases prove to be superior training data, boosting the performance of RL-trained models on benchmarks like LiveCodeBench. All code, datasets, and evaluation scripts will be open-sourced to promote further investigation in LLMs for competitive programming.
While multilingual large language models (LLMs) perform well on high-level tasks like translation and question answering, their ability to handle grammatical gender and morphological agreement remains underexplored. In morphologically rich languages, gender influences verb conjugation, pronouns, and even first-person constructions with explicit and implicit mentions of gender. We introduce MORPHOGEN, a morphologically grounded large-scale benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages: French, Arabic, and Hindi. The core task, GENFORM, requires models to rewrite a first-person sentence in the opposite gender while preserving its meaning and structure. We construct a high-quality synthetic dataset spanning these three languages and benchmark 15 popular multilingual LLMs (2B–70B) on their ability to perform this transformation. Our results reveal significant gaps and interesting insights into how current models handle morphological gender. MORPHOGEN provides a focused diagnostic lens for gender-aware language modeling and lays the groundwork for future research on inclusive and morphology-sensitive NLP.
Effective poster design requires rapidly capturing attention and clearly conveying messages. Inspired by the “contrast effects” principle, we propose ReContraster, the first training-free model to leverage regional contrast to make posters stand out. By emulating the cognitive behaviors of a poster designer, ReContraster introduces the compositional multi-agent system to identify elements, organize layout, and evaluate generated poster candidates. To further ensure harmonious transitions across region boundaries, ReContraster integrates the hybrid denoising strategy during the diffusion process. We additionally contribute a new benchmark dataset for comprehensive evaluation. Seven quantitative metrics and four user studies confirm its superiority over relevant state-of-the-art methods, producing visually striking and aesthetically appealing posters.
Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence
PDF ↗In-Context Learning (ICL) allows large language models to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model’s ability to understand the context, obscuring whether failures arise from data properties or model limitations. Uncertainty decomposition—separating aleatoric from epistemic sources—is particularly crucial in this setting, yet existing methods, designed for standard generation tasks, fail to capture the unique dynamics of ICL. To address this, we introduce a concept of self-function vectors, built upon Bayesian views and the mechanistic interpretability of ICL. These vectors leverage internal model representations to model the latent concept learned during in-context prompting, thereby enabling a direct estimation of aleatoric uncertainty within a Bayesian framework and circumventing the reliance on brittle input or decoding manipulations. Given the lack of established benchmarks and suitable evaluation protocols, we also propose the first and rigorous evaluation framework, initially grounded in synthetic tasks for conceptual development and subsequently extended to real-world datasets, in which aleatoric and epistemic uncertainty can be quantified separately under controlled settings. Moreover, we show it can be used as a practical tool for trustworthy-related applications, such as hallucination detection. Our findings pave a new direction for connecting the quantitative view of uncertainty with the mechanistic understanding of model behavior.
The development of large-scale Visual Question Answering (VQA) datasets has traditionally relied on resource-intensive manual annotation. In addition, most of the existing Arabic VQA datasets focus on culturally-specific and dialect-aware domains. To address these limitations, we propose a new pipeline that leverages Wikipedia template tags to extract the relevant information for each image, which is subsequently utilized by the Large Language Model (LLM) to synthetically generate a new visual question answering dataset. Using this pipeline, we have constructed AraVQA, the most comprehensive Arabic Factoid Visual Question Answering dataset, containing more than 50,000 questions and covering over 20 varied primary subjects within Arabic general knowledge. Our detailed analysis shows that our dataset can serve as a post-training dataset to enhance the performance of existing Visual Language Models (VLMs) on Arabic VQA tasks. Furthermore, we present a novel benchmark, derived from our dataset and validated through manual annotation, that poses more challenges to Arabic VLMs than existing Arabic VQA datasets.
VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels
PDF ↗Video anomaly understanding (VAU) is critical for real-world scenarios. Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. However, progress in anomaly localization is still limited by two key issues. First, most existing video anomaly datasets only annotate segments that are clearly inconsistent with the context, often omitting subsequent segments that are semantically part of the same abnormal event. Second, the field lacks systematic evaluation protocols. To bridge these gaps, we introduce VALU, a new benchmark that explicitly defines anomalies across five semantic levels and provides comprehensive temporal boundaries and detailed textual descriptions for each. Based on these annotations, we design three evaluation tasks that comprehensively assess models’ capabilities across different dimensions, including temporal grounding, anomaly localization, and anomaly detail discrimination. Evaluation results reveal persistent challenges in current models’ capabilities on VAU. We further analyze and discuss these findings, and hope that both VALU and insights will advance research in VAU and the development of Video-LLMs. Our benchmark will be publicly available.
In this paper, we introduce **ReasonEmbed**, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose **ReMixer**, a new data synthesis method that overcomes the triviality problem prevalent in previous synthetic datasets, enabling large-scale production of 82K high-quality training samples. Second, we design **Redapter**, a self-adaptive learning algorithm that dynamically adjusts training each sample’s weight based on its reasoning intensity. This allows the model to effectively capture the complex semantic relationships between queries and documents. Third, we implement ReasonEmbed across multiple backbones of varying sizes, all of which achieve **superior performance** on reasoning-intensive retrieval tasks. Notably, our ReasonEmbed-Qwen3-8B model offers a record-high nDCG@10 score of 38.1 on the BRIGHT benchmark, which significantly outperforms existing text embedding models. We will fully open-source our created resource in ReasonEmbed to push forward the research advancement in this field.
Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI), which measures how effectively each candidate example reduces instruction-following difficulty for semantically related peers. Through systematic experiments, we address three key questions: what constitutes effective instruction tuning data from an in-context perspective, whether sample difficulty correlates with in-context influence, and how in-context influence translates to instruction tuning effectiveness. Experiments across multiple models and benchmarks demonstrate that our method consistently outperforms existing baselines under constrained data budgets, while empirically showing that sample difficulty negatively correlates with in-context influence.
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
PDF ↗Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative think–search loop accumulates long system memories, leading to memory dilution problem. In addition, existing memory management methods struggle to capture fine-grained semantic relations between queries and documents and often lose substantial information. Therefore, we propose MemSearch-o1, an agentic search framework built on reasoning-aligned memory growth and retracing. MemSearch-o1 dynamically grows fine-grained memory fragments from memory seed tokens from the queries, then retraces and deeply refines the memory via a contribution function, and finally reorganizes a globally connected memory path. This shifts memory management from stream-like concatenation to structured, token-level growth with path-based reasoning. Experiments on eight benchmark datasets show that MemSearch-o1 substantially mitigates memory dilution, and more effectively activates the reasoning potential of diverse LLMs, establishing a solid foundation for memory-aware agentic intelligence.
Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three limitations: causal attention in VLM backbones is suboptimal for embedding tasks; scalability issues due to reliance on high-quality labeled paired data for contrastive learning; and limited diversity in training objectives and data. To address these issues, we propose MoCa, a two-stage framework for transforming pre-trained VLMs into bidirectional multimodal embedding models. The first stage, Modality-aware Continual Pre-training, introduces a joint reconstruction objective that simultaneously denoises interleaved texts and images, enhancing bidirectional context-aware reasoning. The second stage, Heterogeneous Contrastive Fine-tuning, leverages diverse, semantically rich multimodal data beyond simple image-caption pairs to enhance generalization and alignment. Our method addresses the stated limitations by introducing bidirectional attention through continual pre-training, scaling effectively with massive unlabeled datasets via joint reconstruction objectives, and utilizing diverse multimodal data for enhanced representation robustness. Experiments demonstrate that MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-arts, and exhibits strong scalability with both model size and training data on MMEB.We have released the model weights and data on our project page https://haon-chen.github.io/MoCa/.
Recently, large language models (LLMs) have driven a systematic shift in the graph ML com- munity through the adoption of text-attributed graphs (TAGs). Although a variety of frameworks have been developed, most fail to properly ad- dress the challenge of data uncertainty in open- world environments. A representative source of such uncertainty is the limited availability of la- bels in large-scale datasets due to high annotation costs, where unlabeled nodes may belong to either known classes or novel, unknown classes. While node-level out-of-distribution detection and con- ventional open-world graph learning attempt to tackle this problem, two core limitations remain: ① Insufficient methods — existing approaches typically optimize semantics or topology in isola- tion for unknown-class rejection, failing to effec- tively integrate textual and structural information in TAGs; ② Incomplete pipelines — most stud- ies conduct only idealized analyses, such as as- suming a predefined number of unknown classes, which restricts practical utility for model updates and long-term deployment. To overcome these issues, we introduce the Open-world Graph Assis- tant (OGA), an LLM-based framework. OGA first performs unknown-class rejection via adaptive la- bel traceability (ALT), harmoniously combining semantic and topological cues, and then applies the graph label annotator (GLA) for unknown- class annotation, allowing unlabeled nodes to con- tribute to model training. In essence, OGA offers a new pipeline that fully automates the handling of unlabeled nodes in open-world environments, and we establish a systematic benchmark cover- ing four key aspects to validate its effectiveness and practicality through extensive experiments.
Deep Learning · Large Language Models
Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates—more data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and judge reliability from pairwise comparisons without reference labels. We establish identifiability up to natural normalizations and prove consistency and asymptotic normality of the maximum likelihood estimator, enabling confidence intervals for score differences and rank comparisons. Across multiple public benchmarks and a newly collected dataset, our method improves agreement with human preferences, achieves higher data efficiency than unweighted baselines, and produces calibrated uncertainty quantification for LLM rankings.
Deep Learning · Large Language Models
Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their implicit reward model and decrease the likelihood of preferred responses. This results in a decrease in the total likelihood assigned to responses seen in the preference dataset, potentially resulting in undesirable behavior. To counteract this undesired side-effect of DAAs, we examine the effect of using objectives that add a regularization term to maintain the total length-normalized probabilities of the chosen and rejected responses. To better understand over-optimization, we investigate how response likelihood changes are distributed over the tokens with and without regularization. We find that a significant portion of the likelihood changes are due to a small set of outlier tokens, which explains how DAAs improve generation quality despite decreasing the likelihoods of chosen responses. We apply the proposed regularization to reference-based (DPO) and reference-free (SimPO) methods and find (1) improved trade-offs between generation quality and general benchmark capability and (2) improvements in reward modeling across datasets. For example, on Llama-3.1-8B-Instruct, we see both a >20\% relative increase in AlpacaEval2 scores and >9\% relative performance gains on general benchmarks. Additionally, we find that the added regularization term effectively mitigates the amount of displacement within preferred responses overall, and for the outlier tokens specifically, by utilizing low-likelihood tokens.
General Machine Learning · Evaluation
Grading in large undergraduate STEM courses often yields minimal feedback due to heavy instructional workloads. We present a large-scale empirical study of AI grading on real, handwritten single-variable calculus work from a major U.S. public research university. Using OCR-conditioned large language models with structured, rubric-guided prompting, our system produces scores and formative feedback for thousands of free-response quiz submissions from nearly 800 students. In a setting with no single ground-truth label, we evaluate performance against official teaching-assistant grades, student surveys, and independent human review, finding strong alignment with TA scoring and a large majority of AI-generated feedback rated as correct or acceptable across quizzes. Beyond calculus, this setting highlights core challenges in OCR-conditioned mathematical reasoning and partial-credit assessment. We analyze key failure modes, propose practical rubric- and prompt-design principles, and introduce a multi-perspective evaluation protocol for reliable, real-course deployment. Building on the dataset and evaluation framework developed here, we outline a standardized benchmark for AI grading of handwritten mathematics to support reproducible comparison and future research.