11 papers
Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers
Yuhan Wang, Shiyu Ni, Zhikai Ding +3
Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question an…
EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation
Zihang Li, Yuhang Wang, Yikun Zong +6
Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffe…
Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models
Yuhang Wang, Yanxu Zhu, Jiaming Zhang +2
Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies. We study whether a reasoning model can synth…
Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Norms
Yuhang Wang, Yanxu Zhu, Jitao Sang
The advanced reasoning capabilities of Large Reasoning Models enable them to thoroughly understand and apply safety policies through deliberate thought processes, thereby improving…
Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI
Jitao Sang, Jinlin Xiao, Jiarun Han +5
The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey…
XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs
Yuzhuo Xiao, Zeyu Han, Yuhan Wang +1
The rapid spread of multimodal misinformation on social media calls for more effective and robust detection methods. Recent advances leveraging multimodal large language models (ML…