all AI news
Dissociation of Faithful and Unfaithful Reasoning in LLMs
May 27, 2024, 4:49 a.m. | Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung, Ramamohan Paturi, Leon Bergen
cs.CL updates on arXiv.org arxiv.org
Abstract: Large language models (LLMs) improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. Our research investigates how LLMs recover from errors in Chain of Thought, reaching the correct final answer despite mistakes in the reasoning text. Through analysis of these error recovery behaviors, we find evidence for unfaithfulness in Chain of Thought, but we also identify many clear examples of faithful error recovery behaviors. We identify …
abstract analysis arxiv chain of thought cs.ai cs.cl errors generate language language models large language large language models llms mistakes performance reasoning research tasks text thought through type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
AI Focused Biochemistry Postdoctoral Fellow
@ Lawrence Berkeley National Lab | Berkeley, CA
Senior Data Engineer
@ Displate | Warsaw
Staff Software Engineer (Data Platform)
@ Phaidra | Remote
Distributed Compute Engineer
@ Magic | San Francisco
Power Platform Developer/Consultant
@ Euromonitor | Bengaluru, Karnataka, India
Finance Project Senior Manager
@ QIMA | London, United Kingdom