Author

Haohan Wang

h-index 7 View on Semantic Scholar

We have 2 of 23 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Understanding Content Moderation in Large Language Models through Restricted Books: From Refusal to Warning

The central finding is a zero-refusal phenomenon: modern LLMs decline to discuss restricted books in only 0.07% of cases, effectively invalidating the premise of jailbreaking research for this content class.

Xuchen Yu, Emily Knox, Hao-Han Wang · 0 citations

2025

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

This work presents a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization, and introduces structured interventions that adapt CoT generation according to the identified...

Haibo Jin, Peiyan Zhang, Man Luo et al. · Neural Information Processin... · 1 citation