問題分解提高了模型生成的推理的忠實度。

摘要

隨著大型語言模型（LLMs）執行更困難的任務，驗證其行為的正確性和安全性變得更加困難。一種應對這個問題的方法是促使LLMs將其推理外顯化，例如，讓它們在回答問題時生成逐步推理（Chain-of-Thought；CoT）。這種推理可能使我們能夠檢查模型執行任務所使用的過程。然而，這種方法依賴於所述推理是否忠實地反映了模型的實際推理，而這並不總是成立。為了提高CoT推理的忠實度，我們讓模型通過將問題分解為子問題來生成推理。基於分解的方法在問答任務上取得了很好的表現，有時接近CoT的表現，同時提高了模型在幾個最近提出的指標上所述推理的忠實度。通過強迫模型在不同上下文中回答更簡單的子問題，我們大大提高了模型生成推理的忠實度，同時仍然實現了部分CoT的性能增益。我們的結果表明，有可能提高模型生成推理的忠實度；持續改進可能導致推理，使我們能夠驗證LLM行為的正確性和安全性。

English

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having them generate step-by-step reasoning as they answer a question (Chain-of-Thought; CoT). The reasoning may enable us to check the process that models use to perform tasks. However, this approach relies on the stated reasoning faithfully reflecting the model's actual reasoning, which is not always the case. To improve over the faithfulness of CoT reasoning, we have models generate reasoning by decomposing questions into subquestions. Decomposition-based methods achieve strong performance on question-answering tasks, sometimes approaching that of CoT while improving the faithfulness of the model's stated reasoning on several recently-proposed metrics. By forcing the model to answer simpler subquestions in separate contexts, we greatly increase the faithfulness of model-generated reasoning over CoT, while still achieving some of the performance gains of CoT. Our results show it is possible to improve the faithfulness of model-generated reasoning; continued improvements may lead to reasoning that enables us to verify the correctness and safety of LLM behavior.

問題分解提高了模型生成的推理的忠實度。

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

摘要

Support