The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension—such as ethnicity or age—can inadvertently affect another, like gender, either mitigating or exacerbating existing disparities. Understanding these interdependencies is crucial for designing fairer generative models, yet measuring such effects quantitatively remains a challenge. To address this, we introduce BiasConnect, a novel tool for analyzing and quantifying bias interactions in TTI models. BiasConnect uses counterfactual interventions along different bias axes to reveal the underlying structure of these interactions and estimates the effect of mitigating one bias axis on another. These estimates show strong correlation (+0.65) with observed post-mitigation outcomes.Building on BiasConnect, we propose InterMit, an intersectional bias mitigation algorithm guided by user-defined target distributions and priority weights. InterMit achieves lower bias (0.33 vs. 0.52) with fewer mitigation steps (2.38 vs. 3.15 average steps), and yields superior image quality compared to traditional techniques. Although our implementation is training-free, InterMit is modular and can be integrated with many existing debiasing approaches for TTI models, making it a flexible and extensible solution.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators (“LLM-as-a-judge”) is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across diverse dialects. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluate five LLMs on their ability to assess toxicity, measuring multilingual, dialectal, and LLM-human consistency. Our findings show that LLMs are sensitive to both dialectal shifts and low-resource multilingual variation, though the most persistent challenge remains aligning their predictions with human judgments.
Language models (LMs) hallucinate. We inquire: Can we detect and mitigate hallucinations before they happen? This work answers this research question in the positive, by showing that the internal representations of LMs provide rich signals that can be used for this purpose. We introduce FactCheckmate, which preemptively detects hallucinations by learning a classifier that predicts whether the LM will hallucinate, based on the model’s hidden states produced over the inputs, before decoding begins. If a hallucination is detected, FactCheckmate then intervenes by adjusting the LM’s hidden states such that the model will produce more factual outputs. FactCheckmate provides fresh insights that the inner workings of LMs can be revealed by their hidden states. Practically, both its detection and mitigation models are lightweight, adding little inference overhead; FactCheckmate proves a more efficient approach for mitigating hallucinations compared to many post-hoc alternatives. We evaluate FactCheckmate over LMs of different scales and model families (including Llama, Mistral, Qwen and Gemma), across a variety of QA datasets from different domains. Our results demonstrate the effectiveness of FactCheckmate, achieving over 70% preemptive detection accuracy. On average, outputs generated by LMs with intervention are 34.4% more factual compared to those without.
A key challenge in Multi-Document Summarization (MDS) is effectively integrating information from multiple sources while maintaining coherence and topical relevance. While Large Language Models (LLMs) have shown impressive results in single-document summarization, their performance on MDS still leaves room for improvement. In this paper, we propose a topic-guided reinforcement learning approach to improve content selection in MDS. We first show that explicitly prompting models with topic labels enhances the informativeness. Building on this insight, we propose a novel topic reward within the Group Relative Policy Optimization (GRPO) framework to measure topic alignment between the generated summary and source documents. Experimental results on the Multi-News and Multi-XScience datasets demonstrate that our method consistently outperforms strong baselines, highlighting the effectiveness of leveraging topical cues in MDS.
We present a broad empirical study of state-of-the-art LLMs and LRMs (Large Reasoning Models) on ProofGrid, a new battery of challenging but tractable logical inference tasks that form a domain-independent test of constraint-based reasoning. The tasks include proof writing and proof checking across propositional and equational logic. We also introduce two novel tasks: proof inpainting and proof gap-filling. Solving these problems requires tracking the global structure of a mathematical argument, writing hierarchical subproofs, maintaining coherence across nested assumptions, performing complex case analyses, applying inference rules, reasoning about identity and term rewriting, and reasoning about proofs themselves. Our experiments reveal impressive performance by top-tier models but also systematic failure modes. Along with the benchmarks, we release a new data resource comprising over 10K formal deduction problems and corresponding proofs.
Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight. Existing methods, which gauge a model’s uncertainty through evaluating self-consistency in responses to the target query, can be misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same target query when answering a knowledge-preserving perturbation of the query. We systematically analyze the model behaviors and demonstrate that this discrepancy stems from suboptimal retrieval of parametric knowledge, often due to contextual biases that prevent consistent access to stored knowledge. We then introduce DiverseAgentEntropy, a novel, theoretically-grounded method employing multi-agent interaction across diverse query variations for uncertainty estimation of black-box LLMs. This approach more accurately assesses an LLM’s true uncertainty and improves hallucination detection, outperforming existing self-consistency based techniques.
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification
PDF ↗Recent studies show the promise of large language models (LLMs) for few-shot tabular classification but highlight challenges due to the variability in structured data. To address this, we propose distilling data into actionable insights to enable robust and effective classification by LLMs. Drawing inspiration from human learning processes, we introduce InsightTab, an insight distillation framework guided by principles of divide-and-conquer, easy-first, and reflective learning. Our approach integrates rule summarization, strategic exemplification, and insight reflection through deep collaboration between LLMs and data modeling techniques. The obtained insights enable LLMs to better align their general knowledge and capabilities with the particular requirements of specific tabular tasks. We extensively evaluate InsightTab on nine datasets. The results demonstrate consistent improvement over state-of-the-art methods. Ablation studies further validate the principle-guided distillation process, while analyses emphasize InsightTab’s effectiveness in leveraging labeled data and managing bias.
Legal claims refer to the plaintiff’s demands in a case and are essential to guiding judicial reasoning and case resolution. While many works have focused on improving the efficiency of legal professionals, the research on helping non-professionals (e.g., plaintiffs) remains unexplored. This paper explores the problem of legal claim generation based on the given case’s facts. First, we construct ClaimGen-CN, the first dataset for Chinese legal claim generation task, from various real-world legal disputes. Additionally, we design an evaluation metric tailored for assessing the generated claims, which encompasses two essential dimensions: factuality and clarity. Building on this, we conduct a comprehensive zero-shot evaluation of state-of-the-art general and legal-domain large language models. Our findings highlight the limitations of the current models in factual precision and expressive clarity, pointing to the need for more targeted development in this domain. To encourage further exploration of this important task, we will make the dataset publicly available.
The accurate trust assessment of multimodal large language models (MLLMs) generated predictions, which can enable selective prediction and improve user confidence, is challenging due to the diverse multi-modal input paradigms. We propose \textbf{F}unctionally \textbf{E}quivalent \textbf{S}ampling for \textbf{T}rust \textbf{A}ssessment (FESTA), a multimodal input sampling technique for MLLMs, that generates an uncertainty measure based on the equivalent and complementary input samplings. The proposed task-preserving sampling approach for uncertainty quantification expands the input space to probe the consistency (through equivalent samples) and sensitivity (through complementary samples) of the model. FESTA uses only input-output access of the model (black-box), and does not require ground truth (unsupervised). The experiments are conducted with various off-the-shelf multi-modal LLMs, on both visual and audio reasoning tasks. The proposed FESTA uncertainty estimate achieves significant improvement (33.3% relative improvement for vision-LLMs and 29.6% relative improvement for audio-LLMs) in selective prediction performance, based on area-under-receiver-operating-characteristic curve (AUROC) metric in detecting mispredictions. The code implementation is open-sourced.
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
PDF ↗Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simultaneously. However, applying this technique to vision-language models (VLMs) presents two fundamental challenges: small language models that could serve as efficient drafters lack the architectural components to process visual inputs, and their token predictions fail to match those of VLM target models that consider visual context. We introduce Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models (MASSV), which transforms existing small language models into effective multimodal drafters through a two-phase approach. MASSV first connects the target VLM’s vision encoder to the draft model via a lightweight trainable projector, then applies self-distilled visual instruction tuning using responses generated by the target VLM to align token predictions. Comprehensive experiments across the Qwen2.5-VL and Gemma3 model families demonstrate that MASSV increases accepted length by up to 30% and delivers end-to-end inference speedups of up to 1.46x compared to conventional text-only drafting baselines on visually-grounded tasks.
Metadata extraction is essential for cataloging and preserving datasets, enabling effective research discovery and reproducibility, especially given the current exponential growth in scientific research. While Masader (CITATION) laid the groundwork for extracting a wide range of metadata attributes from Arabic NLP datasets’ scholarly articles, it relies heavily on manual annotation. In this paper, we present MOLE, a framework that leverages Large Language Models (LLMs) to automatically extract metadata attributes from scientific papers covering datasets of languages other than Arabic. Our schema-driven methodology processes entire documents across multiple input formats and incorporates robust validation mechanisms for consistent output. Additionally, we introduce a new benchmark to evaluate the research progress on this task. Through systematic analysis of context length, few-shot learning, and web browsing integration, we demonstrate that modern LLMs show promising results in automating this task, highlighting the need for further future work improvements to ensure consistent and reliable performance.
Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-the-fly
PDF ↗Drawing real world social inferences usually requires taking into account information from multiple modalities. Language is a particularly powerful source of information in social settings, especially in novel situations where language can provide both abstract information about the environment dynamics and concrete specifics about an agent that cannot be easily visually observed. In this paper, we propose Language-Informed Rational Agent Synthesis (LIRAS), a framework for drawing context-specific social inferences that integrate linguistic and visual inputs. LIRAS frames multimodal social reasoning as a process of constructing structured but situation-specific agent and environment representations – leveraging multimodal language models to parse language and visual inputs into unified symbolic representations, over which a Bayesian inverse planning engine can be run to produce granular probabilistic judgments. On a range of existing and new social reasoning tasks derived from cognitive science experiments, we find that our model (instantiated with a comparatively lightweight VLM) outperforms ablations and state-of-the-art models in capturing human judgments across all domains.
MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
PDF ↗This paper introduces MoRoVoc, the largest dataset for analyzing the regional variation of spoken Romanian. It has more than 93 hours of audio and 88,192 audio samples, balanced between the Romanian language spoken in Romania and the Republic of Moldova. We further propose a multi-target adversarial training framework for speech models that incorporates demographic attributes (i.e., age and gender of the speakers) as adversarial targets, making models discriminative for primary tasks while remaining invariant to secondary attributes. The adversarial coefficients are dynamically adjusted via meta-learning to optimize performance. Our approach yields notable gains: Wav2Vec2-Base achieves 78.21% accuracy for the variation identification of spoken Romanian using gender as an adversarial target, while Wav2Vec2-Large reaches 93.08% accuracy for gender classification when employing both dialect and age as adversarial objectives.
Disentangling Language Understanding and Reasoning Structures in Cross-lingual Chain-of-Thought Prompting
PDF ↗Cross-lingual chain-of-thought prompting techniques have proven effective for investigating diverse reasoning paths in Large Language Models (LLMs), especially for low-resource languages. Despite these empirical gains, the mechanisms underlying cross-lingual improvements remain perplexing. This study, therefore, addresses whether the benefits of cross-lingual prompting arise from language-specific reasoning structures intrinsic to each language, or are simply a consequence of improved comprehension through cross-linguistic exposure. We employ neuron intervention and perturbation techniques to analyze and deactivate language-specific reasoning neurons during cross-lingual prompting, leading to performance disparities across languages, up to 27.4%. Our findings disentangle that these neurons are essential for reasoning in their respective languages, but have minimal effect on reasoning in other languages, providing evidence for the existence of language-specific local reasoning structures and guiding the development of more interpretable and effective multilingual AI systems.
We introduce AMIA, a lightweight, inference-only defense for Large Vision–Language Models (LVLMs) that (1) Automatically Masks a small set of text-irrelevant image patches to disrupt adversarial perturbations, and (2) conducts joint Intention Analysis to uncover and mitigate hidden harmful intents before response generation. Without any retraining, AMIA improves defense success rates across diverse LVLMs and jailbreak benchmarks from an average of 52.4% to 81.7%, preserves general utility with only a 2% average accuracy drop, and incurs only modest inference overhead. Ablation confirms that both masking and intention analysis are essential for robust safety–utility trade-off. Our code will be released.
Mitigating Interviewer Bias in Multimodal Depression Detection: An Approach with Adversarial Learning and Contextual Positional Encoding
PDF ↗Clinical interviews are a standard method for assessing depression. Recent approaches have improved prediction accuracy by focusing on specific questions posed by the interviewer and manually selected question-answer (QA) pairs that target mental health content. However, these methods often neglect the broader conversational context, resulting in limited generalization and reduced robustness, particularly in less structured interviews, which are common in real-world clinical settings. In this work, we develop a multimodal dialogue-level transformer that captures the dynamics of dialogue within each interview by using a combination of sequential positional embedding and question context vectors. In addition to the depression prediction branch, we build an adversarial classifier with a gradient reversal layer to learn shared representations that remain invariant to the types of questions asked during the interview. This approach aims to reduce biased learning and improve the fairness and generalizability of depression detection in diverse clinical interview scenarios. Classification and regression experiments conducted on three real-world interview-based datasets and one synthetic dataset demonstrate the robustness and generalizability of our model.
Event argument extraction identifies arguments for predefined event roles in text. Existing work evaluates this task with exact match (EM), where predicted arguments must align exactly with annotated spans. While suitable for span-based models, this approach falls short for large language models (LLMs), which often generate diverse yet semantically accurate arguments. EM severely underestimates performance by disregarding valid variations. Furthermore, EM evaluation fails to capture implicit arguments (unstated but inferable) and scattered arguments (distributed across a document). These limitations underscore the need for an evaluation framework that better captures models’ actual performance. To bridge this gap, we introduce REGen, a Reliable Evaluation framework for Generative event argument extraction. REGen combines the strengths of exact, relaxed, and LLM-based matching to better align with human judgment. Experiments on six datasets show that REGen reveals an average performance gain of +23.93 F1 over EM, reflecting capabilities overlooked by prior evaluation. Human validation further confirms REGen’s effectiveness, achieving 87.67% alignment with human assessments of argument correctness.
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-search perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and thought to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric.
Designing polymers for targeted applications and accurately predicting their properties is a key challenge in materials science owing to the vast and complex polymer chemical space. While molecular language models have proven effective in solving analogous problems for molecular discovery, similar advancements for polymers are limited. To address this gap, we propose polyBART, a language model-driven polymer discovery capability that enables rapid and accurate exploration of the polymer design space. Central to our approach is Pseudo-polymer SELFIES (PSELFIES), a novel representation that allows for the transfer of molecular language models to the polymer space. polyBART is, to the best of our knowledge, the first language model capable of bidirectional translation between polymer structures and properties, achieving state-of-the-art results in property prediction and design of novel polymers for electrostatic energy storage. Further, polyBART is validated through a combination of both computational and laboratory experiments. We report what we believe is the first successful synthesis and validation of a polymer designed by a language model, predicted to exhibit high thermal degradation temperature and confirmed by our laboratory measurements. Our work presents a generalizable strategy for adapting molecular language models to the polymer space and introduces a polymer foundation model, advancing generative polymer design that may be adapted for a variety of applications.
CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis
PDF ↗Large Language Models (LLMs) are increasingly tasked with analyzing legal texts and citing relevant statutes, yet their reliability is often compromised by general pre-training that ingests legal texts without specialized focus, obscuring the true depth of their legal knowledge. This paper introduces CLaw, a novel benchmark specifically engineered to meticulously evaluate LLMs on Chinese legal knowledge and its application in reasoning. CLaw comprises two key components: (1) a comprehensive, fine-grained corpus of all 306 Chinese national statutes, segmented to the subparagraph level and incorporating precise historical revision timesteps for rigorous recall evaluation (64,849 entries), and (2) a challenging set of 254 case-based reasoning instances derived from China Supreme Court curated materials to assess the practical application of legal knowledge. Our empirical evaluation reveals that most contemporary LLMs significantly struggle to faithfully reproduce legal provisions. As accurate retrieval and citation of legal provisions form the basis of legal reasoning, this deficiency critically undermines the reliability of their responses. We contend that achieving trustworthy legal reasoning in LLMs requires a robust synergy of accurate knowledge retrieval—potentially enhanced through supervised fine-tuning (SFT) or retrieval-augmented generation (RAG)—and strong general reasoning capabilities. This work provides an essential benchmark and critical insights for advancing domain-specific LLM reasoning, particularly within the complex legal sphere.