As Large Language Models (LLMs) are increasingly being employed in real-world
applications in critical domains such as healthcare, it is important to ensure
that the Chain-of-Thought (CoT) reasoning generated by these models faithfully
captures their underlying behavior.
While LLMs are known to generate CoT reasoning that is appealing to humans,
prior studies have shown that these explanations do not accurately reflect the
actual behavior of the underlying LLMs. In this work, we explore the promise of
three broad approaches commonly employed to steer the behavior of LLMs to
enhance the faithfulness of the CoT reasoning generated by LLMs: in-context
learning, fine-tuning, and activation editing. Specifically, we introduce novel
strategies for in-context learning, fine-tuning, and activation editing aimed
at improving the faithfulness of the CoT reasoning. We then carry out extensive
empirical analyses with multiple benchmark datasets to explore the promise of
these strategies. Our analyses indicate that these strategies offer limited
success in improving the faithfulness of the CoT reasoning, with only slight
performance enhancements in controlled scenarios. Activation editing
demonstrated minimal success, while fine-tuning and in-context learning
achieved marginal improvements that failed to generalize across diverse
reasoning and truthful question-answering benchmarks. In summary, our work
underscores the inherent difficulty in eliciting faithful CoT reasoning from
LLMs, suggesting that the current array of approaches may not be sufficient to
address this complex challenge.

大语言模型（LLM）在关键领域，如医疗保健中得到越来越多的应用，为了确保这些模型生成的链式思维（CoT）推理能够忠实地捕捉其基本行为，我们探索了三种常用方法 —— 上下文学习、微调和激活编辑 —— 来指导 LLM 的行为，以提高 CoT 推理的准确性，然而我们的实证分析表明：这些方法在提高 CoT 推理的准确性方面取得的成果有限，只在受控情境中略有性能提升，激活编辑几乎没有成功，而微调和上下文学习的改进效果仅在部分推理和真实问答评估中表现出来，总结来说，我们的工作强调了从 LLMs 中获取准确 CoT 推理的困难性，提示当前的方法可能无法解决这一复杂挑战。