Large language models (LLMs) are reshaping how scientific knowledge is accessed and represented. This study evaluates the extent to which popular and frontier LLMs including GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro recognize scientists, benchmarking their outputs against OpenAlex and Wikipedia. Using a dataset focusing on 100,000 physicists from OpenAlex to evaluate LLM recognition, we uncover substantial disparities: LLMs exhibit selective and inconsistent recognition patterns. Recognition correlates strongly with scholarly impact such as citations, and remains uneven across gender and geography. Women researchers, and researchers from Africa, Asia, and Latin America are significantly underrecognized. We further examine the role of training data provenance, identifying Wikipedia as a potential sources that contributes to recognition gaps. Our findings highlight how LLMs can reflect, and potentially amplify existing disparities in science, underscoring the need for more transparent and inclusive knowledge systems.
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
The increasing volume of academic literature makes it essential for researchers to organize, compare, and contrast collections of documents. Large language models (LLMs) can support this process by generating schemas defining shared aspects along which to compare papers. However, progress on schema generation has been slow due to: (i) ambiguity in reference-based evaluations, and (ii) lack of editing/refinement methods. Our work is the first to address both issues. First, we present an approach for augmenting unannotated table corpora with synthesized intents, and apply it to create a dataset for studying schema generation conditioned on a given information need, thus reducing ambiguity. With this dataset, we show how incorporating table intents significantly improves baseline performance in reconstructing reference schemas. We start by comprehensively benchmarking several single-shot schema generation methods, including prompted LLM workflows and fine-tuned models, showing that smaller, open-weight models can be fine-tuned to be competitive with state-of-the-art prompted LLMs. Next, we propose several LLM-based schema refinement techniques and show that these can further improve schemas generated by these methods.
ProcVQA: Benchmarking the Effects of Structural Properties in Mined Process Visualizations on Vision–Language Model Performance
PDF ↗Vision-Language Models have shown both impressive capabilities and notable failures in data visualization understanding tasks, but we have limited understanding on how specific properties within a visualization type affect model performance. We present ProcVQA, a benchmark designed to analyze how VLM performance can be affected by structure type and structural density of visualizations depicting frequent patterns mined from sequence data. ProcVQA consists of mined process visualizations spanning three structure types (linear sequences, tree, graph) with varying levels of structural density (quantified using the number of nodes and edges), with expert-validated QA pairs on these visualizations. We evaluate 21 proprietary and open-source models on the dataset on two major tasks: visual data extraction (VDE) and visual question answering (VQA) (with four categories of questions). Our analysis reveals three key findings. First, models exhibit steep performance drops on multi-hop reasoning, with question type and structure type impacting the degradation. Second, structural density strongly affects VDE performance: hallucinations and extraction errors increase with edge density, even in frontier models. Third, extraction accuracy does not necessarily translate into strong reasoning ability. By isolating structural factors through controlled visualization generation, ProcVQA enables precise identification of VLM limitations. ProcVQA is available at: https://github.com/kzintas/ProcVQA.
Visual metaphors are a complex vision–language phenomenon that requires both perceptual and conceptual reasoning to understand. They provide a valuable test of a model’s ability to interpret visual input and reason about it with creativity and coherence. We introduce ImageMet, a visual metaphor dataset, featuring 2177 synthetic and 350 human-annotated images. We benchmark several SOTA VLMs on two tasks: Visual Metaphor Captioning (VMC) and Visual Metaphor VQA (VM-VQA). We establish strong baselines by fine-tuning on ImageMet, which yields substantial performance gains in VMC (+4.67% SBERT-Similarity, +4.84% task-specific metric) and VM-VQA (+9.3% Accuracy on average). Additionally, we introduce a task-specific CoT prompting strategy that outperforms standard few-shot baselines (+1.99% in VMC, +5.21% in VM-VQA). We observe that despite strong performance on the VMC task, VLMs still significantly lag behind humans in understanding visual metaphors, indicating that their success often relies on learned associations rather than genuine analytical reasoning. We note that this gap is often obscured in metaphor captioning tasks where the automatic metrics correlate only moderately at best with human judgment (Pearson r < 0.6), highlighting the need for careful, holistic evaluation of the visual metaphor understanding of the models.
Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets. To address this gap, we introduce PEARL, a large-scale Arabic multimodal dataset and benchmark explicitly designed for cultural understanding. Constructed through advanced agentic workflows and extensive human-in-the-loop annotations by 37 annotators from across the Arab world, PEARL comprises over 309K multimodal examples spanning ten culturally significant domains covering all Arab countries. We further provide two robust evaluation benchmarks (PEARL and PEARL-LITE) along with a specialized subset (PEARL-X) explicitly developed to assess nuanced cultural variations. Comprehensive evaluations on state-of-the-art open and proprietary LVLMs demonstrate that reasoning-centric instruction alignment substantially improves models’ cultural grounding compared to conventional scaling methods. PEARL establishes a foundational resource for advancing culturally-informed multimodal modeling research. All datasets and benchmarks are publicly available.
Understanding human social behavior such as recognizing emotions and the social dynamics causing them is an important and challenging problem. While LLMs have made remarkable advances, they are limited to the textual domain and cannot account for the major role that non-verbal cues play in understanding social situations. Vision Language Models (VLMs) can potentially account for this gap, however their ability to make correct inferences over such social cues has received little attention. In this paper, we explore the capabilities of VLMs at social reasoning. We identify a previously overlooked limitation in VLMs: the Visual Social-Pragmatic Inference gap. To target this gap, we propose a new task for VLMs: Visual Social-Pragmatic Inference. We construct a high quality dataset to test the abilities of a VLM for this task and benchmark the performance of several VLMs on it.
Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts
PDF ↗Large vision-language models (LVLMs) have recently achieved significant progress, demonstrating strong capabilities in open-world visual understanding. However, it is not yet clear how LVLMs address demographic biases in real life, especially the disparities across attributes such as gender, skin tone, age and race. In this paper, We empirically investigate visual fairness in several mainstream LVLMs by auditing their performance disparities across demographic attributes using public fairness benchmark datasets (e.g., FACET, UTKFace). Our fairness evaluation framework employs direct and single-choice question prompt on visual question-answering/classification tasks. Despite advancements in visual understanding, our zero-shot prompting results show that both open-source and closed-source LVLMs continue to exhibit fairness issues across different prompts and demographic groups. Furthermore, we propose a potential multi-modal Chain-of-thought (CoT) based strategy for unfairness mitigation, applicable to both open-source and closed-source LVLMs. This approach enhances transparency and offers a scalable solution for addressing fairness, providing a solid foundation for future research and practical efforts in unfairness mitigation. The dataset and code used in this study are publicly available at this GitHub Repository.
Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding prompts, remains underexplored. In this work, we introduce code decomposition attacks, where a malicious coding task is broken down into a series of seemingly benign subtasks across multiple conversational turns to evade safety filters. To facilitate systematic evaluation, we introduce MOCHA, a large-scale benchmark designed to evaluate the robustness of code LLMs against both single-turn and multi-turn malicious prompts. Empirical results across open- and closed-source models reveal persistent vulnerabilities, especially under multi-turn scenarios. Fine-tuning on MOCHA improves rejection rates while preserving coding ability, and importantly, enhances robustness on external adversarial datasets with up to 32.4% increase in rejection rates without any additional supervision.
Natural Language Processing (NLP) has catalyzed a paradigm shift in Computer-Aided Synthesis Planning (CASP), reframing chemical synthesis prediction as a sequence-to-sequence modeling problem over molecular string representations like SMILES. This framing has enabled the direct application of language models to chemistry, yielding impressive benchmark scores on the USPTO dataset, a large text corpus of reactions extracted from US patents. However, we show that USPTO’s patent-derived data are both industrially biased and incomplete. They omit many fundamental transformations essential for practical real-world synthesis. Consequently, models trained exclusively on USPTO perform poorly on simple, pharmaceutically relevant reactions despite high benchmark scores. Our findings highlight a broader concern in applying standard NLP pipelines to scientific domains without rethinking data and evaluation: models may learn dataset artifacts rather than domain reasoning. We argue for the development of chemically meaningful benchmarks, greater data diversity, and interdisciplinary dialogue between the NLP community and domain experts to ensure real-world applicability.
Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them
PDF ↗We investigate the use of LLM-generated data for continual pretraining of transformer encoder models in specialized domains with limited training data, using the scientific domain of invasion biology as a case study. To this end, we leverage domain-specific ontologies by enriching them with LLM-generated data and pretraining the encoder model as an ontology-informed embedding model for concept definitions. To evaluate the effectiveness of this method, we compile a benchmark specifically designed for assessing model performance in invasion biology. After demonstrating substantial improvements over standard MLM pretraining, we investigate the feasibility of applying the proposed approach to domains without comprehensive ontologies by substituting ontological concepts with concepts automatically extracted from a small corpus of scientific abstracts and establishing relationships between concepts through distributional statistics. Our results demonstrate that this automated approach achieves comparable performance using only a small set of scientific abstracts, resulting in a fully automated pipeline for enhancing domain-specific understanding of small encoder models that is especially suited for application in low-resource settings and achieves performance comparable to masked language modeling pretraining on much larger datasets.
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities
PDF ↗Recent advancements in 2D multimodal large language models (MLLMs) have significantly improved performance in vision-language tasks. However, extending these capabilities to 3D environments remains a distinct challenge due to the complexity of spatial reasoning. Nevertheless, existing 3D benchmarks often lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning. To address this gap, we introduce NUMINA, the first Natural Understanding benchmark for Multi-dimensional Intelligence and Numerical reasoning Abilities to enhance multimodal indoor perceptual understanding. NUMINA features multi-scale annotations and various question-answer pairs, generated using NUMINA-Flow, an automated annotation pipeline that integrates LLM rewriting and rule-based self-verification. We evaluate the performance of various state-of-the-art LLMs on NUMINA following the Chat-Scene framework, demonstrating that current LLMs struggle with multimodal numerical reasoning, particularly in performing precise computations such as distance and volume estimation, highlighting the need for further advancements in 3D models. The dataset and source codes can be obtained from https://github.com/fengshun124/NUMINA.
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models
PDF ↗As large language models (LLMs) increasingly permeate the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance. Existing financial benchmarks often suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation. To address these limitations, we introduce Golden Touchstone, a comprehensive bilingual benchmark for financial LLMs, encompassing eight core financial NLP tasks in both Chinese and English. Developed from extensive open-source data collection and industry-specific demands, this benchmark thoroughly assesses models’ language understanding and generation capabilities. Through comparative analysis of major models such as GPT-4o, Llama3, FinGPT, and FinMA, we reveal their strengths and limitations in processing complex financial information. Additionally, we open-source Touchstone-GPT, a financial LLM trained through continual pre-training and instruction tuning, which demonstrates strong performance on the bilingual benchmark but still has limitations in specific tasks. This research provides a practical evaluation tool for financial LLMs and guides future development and optimization.The source code for Golden Touchstone and model weight of Touchstone-GPT have been made publicly available at https://github.com/IDEA-FinAI/Golden-Touchstone.
Perspective-driven Preference Optimization with Entropy Maximization for Diverse Argument Generation
PDF ↗In subjective natural language generation tasks, generating diverse perspectives is essential for fostering balanced discourse and mitigating bias. Argument generation with diverse perspectives plays a vital role in advancing the understanding of controversial claims. Despite the strong generative capabilities of large language models (LLMs), the diversity of perspectives remains insufficiently explored within argument generation task. Moreover, there remains a significant research gap in developing methods that explicitly generate multi-perspective arguments under the quality control of claim-stance alignment constraints. In this paper, we propose POEM, a \textbf{P}erspective-aware Preference \textbf{O}ptimization with \textbf{E}ntropy \textbf{M}aximization framework for diverse argument generation. It enhances perspective diversity through preference optimization based on the constructed preference dataset via perspective mining and diversity measuring. It further introduces entropy maximization to promote perspective diversity by encouraging dispersed semantic representations among the generated arguments. Experimental results on claim-stance argument generation benchmarks show that POEM is capable of generating diverse arguments while maintaining comparable performances in claim and stance controllability as well as text quality compared to the state-of-the-art baselines and human evaluation.
Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural context in multimodal translation. We introduce CaMMT, a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. Using this dataset, we evaluate five Vision Language Models (VLMs) in text-only and text+image settings. Through automatic and human evaluations, we find that visual context generally improves translation quality, especially in handling Culturally-Specific Items (CSIs), disambiguation, and correct gender marking. By releasing CaMMT, our objective is to support broader efforts to build and evaluate multimodal translation systems that are better aligned with cultural nuance and regional variations.
Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
PDF ↗Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning—such as solving Olympiad-level physics problems—remains largely unexplored. Inspired by the way students prepare for competitions by reviewing past problems, we investigate the potential of RAG to enhance physics reasoning in foundation models. We introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics, enabling systematic study of retrieval-based reasoning. PhoPile includes diagrams, graphs, and equations, capturing the inherently multimodal nature of physics problem solving. Using PhoPile, we benchmark RAG-augmented foundation models, covering both large language models (LLMs) and large multimodal models (LMMs) with multiple retrievers. Our results demonstrate that integrating retrieval with physics corpora can improve model performance, while also highlighting challenges that motivate further research in retrieval-augmented physics reasoning.
Recent advancements in Aspect-Based Sentiment Analysis (ABSA) have shown promising results, yet the semantics derived solely from textual data remain limited. To overcome this challenge, we propose a novel approach by venturing into the unexplored territory of generating sentimental images. Our method introduce a synthetic image generation framework tailored to produce images that are highly congruent with both textual and sentimental information for aspect-based sentiment analysis. Specifically, we firstly develop a supervised image generation model to generate synthetic images with alignment to both text and sentiment information. Furthermore, we employ a visual refinement technique to substantially enhance the quality and pertinence of the generated images. After that, we propose a multi-modal model to integrate both the original text and the synthetic images for aspect-based sentiment analysis. Extensive evaluations on multiple benchmark datasets demonstrate that our model significantly outperforms state-of-the-art methods. These results highlight the effectiveness of our supervised image generation approach in enhancing ABSA.
We study the capabilities of large language models (LLMs) in detecting fine-grained anomalies in tabular data. Specifically, we examine: (1) how well LLMs can identify diverse anomaly types including factual, logical, temporal, and value-based errors; (2) the impact of prompt design and prompting strategies; and (3) the effect of table structure and anomaly type on detection accuracy. To this end, we introduce TABARD, a new benchmark constructed by perturbing tables from WikiTQ, FeTaQA, Spider, and BEAVER. The dataset spans multiple domains and eight anomaly categories, including paired clean and corrupted tables. We evaluate LLMs using direct, indirect, and Chain-of-Thought (CoT) prompting. Our results reveal notable limitations in standard prompting, especially for complex reasoning tasks and longer tables. To overcome these issues, we propose a unified framework combining multi-step prompting, self-verification, and constraint-based rule execution. Our approach significantly improves precision and recall, offering a promising direction for robust and interpretable anomaly detection in tables.
A core part of scientific peer review involves providing expert critiques that directly assess the scientific claims a paper makes. While it is now possible to automatically generate plausible (if generic) reviews, ensuring that these reviews are sound and grounded in the papers’ claims remains challenging. To facilitate LLM benchmarking on these challenges, we introduce CLAIMCHECK, an annotated dataset of NeurIPS 2023 and 2024 submissions and reviews mined from OpenReview. CLAIMCHECK is richly annotated by ML experts for weakness statements in the reviews and the paper claims that they dispute, as well as fine-grained labels of the validity, objectivity, and type of the identified weaknesses. We benchmark several LLMs on three claim-centric tasks supported by CLAIMCHECK, requiring models to (1) associate weaknesses with the claims they dispute, (2) predict fine-grained labels for weaknesses and rewrite the weaknesses to enhance their specificity, and (3) verify a paper’s claims with grounded reasoning. Our experiments reveal that cutting-edge LLMs, while capable of predicting weakness labels in (2), continue to underperform relative to human experts on all other tasks.
TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalities
PDF ↗The widespread presence of incomplete modalities in multimodal data poses a significant challenge to achieving accurate rumor detection. Existing multimodal rumor detection methods primarily focus on learning joint modality representations from complete multimodal training data, rendering them ineffective in addressing the common occurrence of missing modalities in real-world scenarios. In this paper, we propose a hierarchical soft prompt model TriSPrompt, which integrates three types of prompts, i.e., modality-aware (MA) prompt, modality-missing (MM) prompt, and mutual-views (MV) prompt, to effectively detect rumors in incomplete multimodal data. The MA prompt captures both heterogeneous information from specific modalities and homogeneous features from available data, aiding in modality recovery. The MM prompt models missing states in incomplete data, enhancing the model’s adaptability to missing information. The MV prompt learns relationships between subjective (i.e., text and image) and objective (i.e., comments) perspectives, effectively detecting rumors. Extensive experiments on three real-world benchmarks demonstrate that TriSPrompt achieves an accuracy gain of over 13% compared to state-of-the-art methods. The codes and datasets are available at https: //anonymous.4open.science/r/code-3E88.
Large Multimodal Models (LMMs) are increasingly vulnerable to AI-generated extremist content, including photorealistic images and text, which can be used to bypass safety mechanisms and generate harmful outputs. However, existing datasets for evaluating LMM robustness offer limited exploration of extremist content, often lacking AI-generated images, diverse image generation models, and comprehensive coverage of historical events, which hinders a complete assessment of model vulnerabilities. To fill this gap, we introduce ExtremeAIGC, a benchmark dataset and evaluation framework designed to assess LMM vulnerabilities against such content. ExtremeAIGC simulates real-world events and malicious use cases by curating diverse text and image based examples crafted using state-of-the-art image generation techniques. Our study reveals alarming weaknesses in LMMs, demonstrating that even cutting-edge safety measures fail to prevent the generation of extremist material. We systematically quantify the success rates of various attack strategies, exposing critical gaps in current defenses and emphasizing the need for more robust mitigation strategies. The code and data can be found at https://github.com/TheProParadox/ExtremeAIGC.