Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps
When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. However, despite much work on CoT prompting, it is unclear if CoT reasoning is faithful to the models' parameteric beliefs. We introduce a framework for measuring parametric faithfulness of generated reasoning, and propose Faithfulness by Unlearning Reasoning steps (FUR), an instance of this framework. FUR erases information contained in reasoning steps from model parameters. We perform experiments unlearning CoTs of four LMs prompted on four multi-choice question answering (MCQA) datasets. Our experiments show that FUR is frequently able to change the underlying models' prediction by unlearning key steps, indicating when a CoT is parametrically faithful. Further analysis shows that CoTs generated by models post-unlearning support different answers, hinting at a deeper effect of unlearning. Importantly, CoT steps identified as important by FUR do not align well with human notions of plausbility, emphasizing the need for specialized alignment
Code (1)
Tasks
Question AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faith…
Reinforcement LearningJourney Before Destination: On the importance of Visual Faithfulness in Slow Thinking
Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually u…
Multimodal ReasoningMeasuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is…
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning
Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps. Existing self-evaluation approaches are prone to in…
Investigating Faithfulness in Large Audio Language Models
Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks. While these models can generate Chain-of-Thought (CoT) explanations, the f…
Multimodal Reasoning