Kevin Du

@kevin-du · 2 works

Recent posts by Kevin Du

• Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning - Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as such, using LLM judges to diagnose… · Paper · arxiv.org
• It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief - Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior… · Paper · arxiv.org

Topics Kevin Du posts about

• AI Models on Instagram - 1 post · Best AI Models creators