While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment results show that the supervised fine-tuning technique contributes greatly to the models’ performance. The dataset will be publicly available.
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
12,319篇论文匹配“Datasets and Benchmarks”
第 328 / 616 页
Large language models (LLMs) have been well-researched in various long-context tasks. However, the scarcity of long-context summarization datasets hinders progress in this area. To address this, we introduce CNNSum, a multi-scale long-context summarization benchmark based on Chinese novels, featuring human-driven annotations across four subsets totaling 695 samples, with lengths ranging from 16k to 128k. We benchmark numerous LLMs and conduct detailed human assessments to summarize abnormal output types. Furthermore, we extensively explore how to improve long-context summarization. In our study: (1) Advanced LLMs may generate much subjective commentary, leading to vague summaries. (2) Currently, long-context summarization mainly relies on memory ability. The advantages of Large LLMs are hard to utilize, thus small LLMs are more cost-effective. (3) Different prompt types paired with various version models may cause large performance gaps. In further fine-tuning, these can be mitigated, and the Base version models perform better. (4) LLMs with RoPE-base scaled exhibit strong extrapolation potential; using short-context data can significantly improve long-context summarization performance. However, further applying other interpolation methods requires careful selection. (5) CNNSum provides more reliable evaluation results than other benchmarks. We release CNNSum to advance future research.
Predictive analysis is a cornerstone of modern decision-making, with applications in various domains. Large Language Models (LLMs) have emerged as powerful tools in enabling nuanced, knowledge-intensive conversations, thus aiding in complex decision-making tasks. With the burgeoning expectation to harness LLMs for predictive analysis, there is an urgent need to systematically assess their capability in this domain. However, there are no relevant evaluations in existing studies. To bridge this gap, we introduce the PredictiQ benchmark, which integrates 1130 sophisticated predictive analysis queries originating from 44 real-world datasets of 8 diverse fields. We design an evaluation protocol considering text analysis, code generation, and their alignment. Twelve renowned LLMs are evaluated, offering insights into their practical use in predictive analysis.
Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to jailbreak attacks, their ability to generate more targeted and organized content can lead to greater harm. Although some studies claim that reasoning enables safer LRMs against existing LLM attacks, they overlook the inherent flaws within the reasoning process itself. To address this gap, we propose the first jailbreak attack targeting LRMs, exploiting their unique vulnerabilities stemming from the advanced reasoning capabilities. Specifically, we introduce a Chaos Machine, a novel component to transform attack prompts with diverse one-to-one mappings. The chaos mappings iteratively generated by the machine are embedded into the reasoning chain, which strengthens the variability and complexity and also promotes a more robust attack. Based on this, we construct the Mousetrap framework, which makes attacks projected into nonlinear-like low sample spaces with mismatched generalization enhanced. Also, due to the more competing objectives, LRMs gradually maintain the inertia of unpredictable iterative reasoning and fall into our trap. Success rates of the Mousetrap attacking o1-mini, Claude-Sonnet and Gemini-Thinking are as high as 96%, 86% and 98% respectively on our toxic dataset Trotter. On benchmarks such as AdvBench, StrongREJECT, and HarmBench, attacking Claude-Sonnet, well-known for its safety, Mousetrap can astonishingly achieve success rates of 87.5%, 86.58% and 93.13% respectively. Attention: This paper contains inappropriate, offensive and harmful content.
Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. Nonetheless, most existing TEC-VQA benchmarks focus on high-resource languages like English and Chinese. Despite pioneering works expanding multilingual QA pairs in non-text-centric VQA datasets through translation engines, the translation-based protocol encounters a substantial “visual-textual misalignment” problem when applied to TEC-VQA. Specifically, it prioritizes the text in question-answer pairs while disregarding the visual text present in images. Moreover, it fails to address complexities related to nuanced meaning, contextual distortion, language bias, and question-type diversity. In this work, we tackle multilingual TEC-VQA by introducing MTVQA, the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. Further, by comprehensively evaluating numerous state-of-the-art Multimodal Large Language Models (MLLMs), including Qwen2.5-VL, InternVL-2.5, GPT-4o, GPT-4V, Claude3, and Gemini, on the MTVQA benchmark, it is evident that there is still a large room for performance improvement (InternVL-2.5 scoring 32.2 versus 79.7 for human performance), underscoring the value of MTVQA. By providing a dataset with nuanced multilingual annotations, MTVQA aims to set a new standard for benchmarks, fostering advancements in multilingual visual text comprehension.
Text style transfer (TST) aims to flexibly adjust the style of text while preserving its core content. Although large language models (LLMs) excel in TST tasks, they often face unidirectional issues due to imbalanced training data and their tendency to generate safer responses. These challenges present a significant obstacle in achieving effective style transfer. To address this issue, we propose a novel method for text style transfer based on neuron activation modulation (NAM-TST). This approach identifies neurons related to style through gradient-based activation difference analysis and calculates the activation differences between the source and target styles. During text generation, we use the activation difference to align the activation values of style-related neurons with those of the target style to guide the model in performing the transfer. This strategy enables the model to generate text that satisfies specific style requirements, effectively mitigating the unidirectional issue inherent in LLMs during style transfer. Experiments on benchmark datasets demonstrate that NAM-TST significantly enhances style transfer quality while preserving content consistency.
The automation of scientific research through large language models (LLMs) presents significant opportunities but faces critical challenges in knowledge synthesis and quality assurance. We introduce Feedback-Refined Agent Methodology (FRAME), a novel framework that enhances medical paper generation through iterative refinement and structured feedback. Our approach comprises three key innovations: (1) A structured dataset construction method that decomposes 4,287 medical papers into essential research components through iterative refinement; (2) A tripartite architecture integrating Generator, Evaluator, and Reflector agents that progressively improve content quality through metric-driven feedback; and (3) A comprehensive evaluation framework that combines statistical metrics with human-grounded benchmarks. Experimental results demonstrate FRAME’s effectiveness, achieving significant improvements over conventional approaches across multiple models (9.91% average gain with DeepSeek V3, comparable improvements with GPT-4o Mini) and evaluation dimensions. Human evaluation confirms that FRAME-generated papers achieve quality comparable to human-authored works, with particular strength in synthesizing future research directions. The results demonstrated our work could efficiently assist medical research by building a robust foundation for automated medical research paper generation while maintaining rigorous academic standards.
Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework
PDF ↗While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we introduce a comprehensive benchmark covering a wide range of temporal granularities, designed to systematically evaluate LLMs’ capabilities in explainable temporal reasoning. Furthermore, our findings reveal that LLMs struggle to deliver convincing explanations when relying solely on textual information. To address challenge, we propose GETER, a novel structure-aware generative framework that integrates Graph structures with text for Explainable TEmporal Reasoning. Specifically, we first leverage temporal knowledge graphs to develop a temporal encoder that captures structural information for the query. Subsequently, we introduce a structure-text prefix adapter to map graph structure features into the text embedding space. Finally, LLMs generate explanation text by seamlessly integrating the soft graph token with instruction-tuning prompt tokens. Experimental results indicate that GETER achieves state-of-the-art performance while also demonstrating robust generalization capabilities. Our dataset and code are available at https://github.com/carryTatum/GETER.
We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing code-focused resources typically fail to ensure either the breadth of coverage (e.g., spanning simple coding tasks to advanced algorithmic problems) or verifiable correctness (e.g., unit tests). In contrast, KodCode comprises question–solution–test triplets that are systematically validated via a self-verification procedure. Our pipeline begins by synthesizing a broad range of coding questions, then generates solutions and test cases with additional attempts allocated to challenging problems. Finally, post-training data synthesis is done by rewriting questions into diverse formats and generating responses under a test-based reject sampling procedure from a reasoning model (DeepSeek R1). This pipeline yields a large-scale, robust and diverse coding dataset. It is suitable for supervised fine-tuning and the paired unit tests also provide great potential for RL tuning. Fine-tuning experiments on coding benchmarks (HumanEval(+), MBPP(+), BigCodeBench, and LiveCodeBench) demonstrate that KodCode-tuned models achieve state-of-the-art performance, surpassing models like Qwen2.5-Coder-32B-Instruct and DeepSeek-R1-Distill-Llama-70B.
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness diminishes when applied to private datasets (e.g., company-specific proprietary data), which often contain specialized terminology and lingo. In this work, we introduce BMEmbed, a novel method for adapting general-purpose text embedding models to private datasets. By leveraging the well-established keyword-based retrieval technique (BM25), we construct supervisory signals from the ranking of keyword-based retrieval results to facilitate model adaptation. We evaluate BMEmbed across a range of domains, datasets, and models, showing consistent improvements in retrieval performance. Moreover, we provide empirical insights into how BM25-based signals contribute to improving embeddings by fostering alignment and uniformity, highlighting the value of this approach in adapting models to domain-specific data. We release the source code for the research community.
Autonomous graphical user interface (GUI) agents powered by multimodal large language models have shown great promise. However, a critical yet underexplored issue persists: over-execution, where the agent executes tasks in a fully autonomous way, without adequate assessment of its action confidence to compromise an adaptive human-agent collaboration. This poses substantial risks in complex scenarios, such as those involving ambiguous user instructions, unexpected interruptions, and environmental hijacks. To address the issue, we introduce OS-Kairos, an adaptive GUI agent capable of predicting confidence levels at each interaction step and efficiently deciding whether to act autonomously or seek human intervention. OS-Kairos is developed through two key mechanisms: (i) collaborative probing that annotates confidence scores at each interaction step; (ii) confidence-driven interaction that leverages these confidence scores to elicit the ability of adaptive interaction. Experimental results show that OS-Kairos substantially outperforms existing models on our curated dataset featuring complex scenarios, as well as on established benchmarks such as AITZ and Meta-GUI, with 24.59%~87.29% improvements in task success rate. OS-Kairos facilitates an adaptive human-agent collaboration, prioritizing effectiveness, generality, scalability, and efficiency for real-world GUI interaction. The dataset and codes are available at Anonymous.
Large Language Models (LLMs) have shown remarkable capabilities across various tasks, but their deployment in high-stake domains requires consistent and coherent behavior across multiple rounds of user interaction. This paper introduces a comprehensive framework for evaluating and improving LLM response consistency, making three key contributions . First, we introduce Position-Weighted Consistency (PWC), a metric designed to capture both the importance of early-stage stability and recovery patterns in multi-turn interactions. Second, we present MT-Consistency, a carefully curated benchmark dataset spanning diverse domains and difficulty levels, specifically designed to evaluate LLM consistency under various challenging follow-up scenarios. Third, we introduce Confidence-Aware Response Generation (CARG), a framework that significantly improves response stability by explicitly integrating internal model confidence scores during the generation process. Experimental results demonstrate that CARG significantly improves response stability without sacrificing accuracy, offering a practical path toward more dependable LLM behavior in critical, real-world deployments.
The improvement of LLMs’ instruction-following capabilities depends critically on the availability of high-quality instruction-response pairs. While existing automatic data synthetic methods alleviate the burden of manual curation, they often rely heavily on either the quality of seed data or strong assumptions about the structure and content of web documents. To tackle these challenges, we propose Web Reconstruction (WebR), a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions. Leveraging the inherent diversity of raw web content, we conceptualize web reconstruction as an instruction-tuning data synthesis task via a novel dual-perspective paradigm—Web as Instruction and Web as Response—where each web document is designated as either the input or output role to trigger the reconstruction process. Comprehensive experiments show that datasets generated by WebR outperform state-of-the-art baselines by up to 16.65% across four instruction-following benchmarks. Notably, WebR demonstrates superior compatibility, data efficiency, and scalability, enabling enhanced domain adaptation with minimal effort.
Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We propose a proof-of-concept framework that projects how model-generated advice could propagate through societal systems on a macroscopic scale over time, enabling more robust alignment. To assess the long-term safety awareness of language models, we also introduce a dataset of 100 indirect harm scenarios, testing models’ ability to foresee adverse, non-obvious outcomes from seemingly harmless user prompts. Our approach achieves not only over 20% improvement on the new dataset but also an average win rate exceeding 70% against strong baselines on existing safety benchmarks (AdvBench, SafeRLHF, WildGuardMix), suggesting a promising direction for safer agents.
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
PDF ↗Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: (i) reliance on handcrafted features that limit generalizability, (ii) difficulty in capturing fine-grained traits like coherence and argumentation, and (iii) inability to handle multimodal contexts. In the era of Multimodal Large Language Models (MLLMs), we propose **EssayJudge**, the **first multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits**. By leveraging MLLMs’ strengths in trait-specific scoring and multimodal context understanding, EssayJudge aims to offer precise, context-rich evaluations without manual feature engineering, addressing longstanding AES limitations. Our experiments with 18 representative MLLMs reveal gaps in AES performance compared to human evaluation, particularly in discourse-level traits, highlighting the need for further advancements in MLLM-based AES research. Our dataset and code will be available upon acceptance.
Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation benchmarks, their performance still falls substantially short of human-level capabilities in more realistic online settings. A key bottleneck is the lack of diverse and large-scale trajectory-level datasets across various domains, which are expensive to collect. In this paper, we address this challenge by developing a scalable recipe to synthesize the largest and most diverse trajectory-level dataset to date, containing over 94K successful multimodal web trajectories, spanning 49K unique URLs, 720K screenshots, and 33M web elements. In particular, we leverage extensive web exploration and refinement to obtain diverse task intents. The average cost is 28 cents per successful trajectory, making it affordable to a wide range of users in the community. Leveraging this dataset, we train Explorer, a multimodal web agent, and demonstrate strong performance on both offline and online web agent benchmarks such as Mind2Web-Live, Multimodal-Mind2Web, and MiniWob++. Additionally, our experiments highlight data scaling as a key driver for improving web agent capabilities. We hope this study makes state-of-the-art LMM-based agent research at a larger scale more accessible.
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
PDF ↗Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks. In this paper, we identify a critical safety gap: while LLMs are adept at detecting jailbreak prompts, they often produce unsafe responses when directly processing these inputs. Inspired by this insight, we propose SAGE(Self-Aware Guard Enhancement), a training-free defense strategy designed to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability. SAGE consists of two core components: a Discriminative Analysis Module and a Discriminative Response Module, enhancing resilience against sophisticated jailbreak attempts through flexible safety discrimination instructions. Extensive experiments demonstrate SAGE’s effectiveness and robustness across various open-source and closed-source LLMs of different sizes and architectures, achieving an average 99% defense success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks. We further conduct mechanistic interpretability analysis through hidden states and attention distributions, revealing the underlying mechanisms of this detection-generation discrepancy. Our work thus contributes to developing future LLMs with coherent safety awareness and generation behavior. Our code and datasets are publicly available at https://github.com/NJUNLP/SAGE.
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
PDF ↗Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinations that require advanced reasoning. Current benchmarks for relation hallucinations lack detailed evaluation and effective mitigation, and their datasets often suffer from biases due to systematic annotation processes. To address these challenges, we introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples. We provide a systematic definition of relation hallucinations, integrating perceptive and cognitive perspectives, and construct a relation-based corpus using the Visual Genome scene graph dataset. Our comparative evaluation reveals significant limitations in current MLLMs’ ability to handle relation hallucinations. Additionally, we propose a novel confidence-based mitigation strategy, which reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. Our work offers valuable insights for achieving trustworthy multimodal intelligence. The dataset and code are released at https://github.com/JackChen-seu/Reefknot.
This paper studies the problem of text-attributed graph clustering, which aims to cluster each node into different groups using both textual attributes and structural information. Although graph neural networks (GNNs) have been proposed to solve this problem, their performance is usually limited when uncertain nodes are near the cluster boundaries due to label scarcity. In this paper, we introduce a new perspective of leveraging large language models (LLMs) to enhance text-attributed graph clustering and develop a novel approach named Multi-agent Collaboration with Ranking Guidance (MARK). The core of our MARK is to generate reliable guidance using the collaboration of three LLM-based agents as ranking-based supervision signals. In particular, we first conduct the coarse graph clustering, and utilize a concept agent to induce the semantics of each cluster. Then, we infer the robustness under perturbations to identify uncertain nodes and use a generation agent to produce synthetic text that closely aligns with their topology. An inference agent is adopted to provide the ranking semantics for each uncertain node in comparison to its synthetic counterpart. The consistent feedback between uncertain and synthetic texts is identified as reliable guidance for fine-tuning the clustering model within a ranking-based supervision objective. Experimental results on various benchmark datasets validate the effectiveness of the proposed MARK compared with competing baselines.
As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets are focus on English andNorth American culture, and their bias categories are not fully applicable to other cultures. The datasets grounded in the Chinese language and culture are scarce. More importantly, these datasets usually only support single evaluation task and cannot evaluate the bias from multiple aspects in LLMs. To address these issues, we present a Multi-task Chinese Bias Evaluation Benchmark (McBE) that includes 4,077 bias evaluation instances, covering 12 single bias categories, 82 subcategories and introducing 5 evaluation tasks, providing extensive category coverage, content diversity, and measuring comprehensiveness. Additionally, we evaluate several popular LLMs from different series and with parameter sizes. In general, all these LLMs demonstrated varying degrees of bias. We conduct an in-depth analysis of results, offering novel insights into bias in LLMs.