How Ambiguous Are the Rationales for Natural Language Reasoning? A Simple Approach to Handling Rationale Uncertainty
This work addresses the challenge of rationale uncertainty for improving language model reasoning, but it is incremental as it builds on existing methods for handling ambiguous rationales.
The study tackled the problem of ambiguous rationales in natural language reasoning by assessing their impact through entropy and uncertainty, and proposed a method to guide models to choose between reasoning paths based on ambiguity, resulting in robust performance, especially in adversarial scenarios with inconsistent rationale quality.
The quality of rationales is essential in the reasoning capabilities of language models. Rationales not only enhance reasoning performance in complex natural language tasks but also justify model decisions. However, obtaining impeccable rationales is often impossible. Our study aims to investigate how ambiguous rationales play in model performances of natural language reasoning. We first assess the ambiguity of rationales through the lens of entropy and uncertainty in model prior beliefs, exploring its impact on task performance. We then propose a simple way to guide models to choose between two different reasoning paths depending on the ambiguity of the rationales. Our empirical results demonstrate that this approach leads to robust performance, particularly in adversarial scenarios where rationale quality is inconsistent.