8 papers
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
Yuxi Sun, Wenbo Shang, Wei Gao +2
In RAG-based fact-checking, LLMs are increasingly used as verifiers to check given claims against retrieved evidence. Their parametric knowledge can induce pre-evidence tendencies…
REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
Chuyi Kong, Wei Gao, Jing Ma +2
The prevalence of fake news on social media demands automated fact-checking systems to provide accurate verdicts with faithful explanations. However, existing large language model…
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning
Yuxi Sun, Aoqi Zuo, Haotian Xie +3
Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps. Existing se…
On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation
Wenbo Shang, Yuxi Sun, Jing Ma +1
Humor is a commonly used and intricate human language in daily life. Humor generation, especially in multi-modal scenarios, is a challenging task for large language models (LLMs),…
Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
Yuxi Sun, Wei Gao, Hongzhan Lin +2
Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crim…
CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
Yuxi Sun, Aoqi Zuo, Wei Gao +1
Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to re…