Faithful and Unfaithful Error Recovery in Chain of Thought

Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung, Ramamohan Paturi, Leon Bergen

Research Area: Science of LMs

Keywords: chain of thought, error recovery, reasoning, faithfulness

TL;DR: LLMs exhibit both faithful and unfaithful error recovery behaviors when using Chain of Thought reasoning, with various factors influencing the occurrence of each type of recovery.

Abstract:

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through analysis of error recovery behaviors, we find evidence for unfaithfulness in Chain of Thought, which occurs when models arrive at the correct answer despite invalid reasoning text. We identify factors that shift LLM recovery behavior: LLMs recover more frequently from obvious errors and in contexts that provide more evidence for the correct answer. Critically, these factors have divergent effects on faithful and unfaithful recoveries.
Our results indicate that there are distinct mechanisms driving faithful and unfaithful error recoveries. Selective targeting of these mechanisms may be able to drive down the rate of unfaithful reasoning and improve model interpretability.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1322