On the Intersection of Self-Correction and Trust in Language Models
This work addresses trustworthiness concerns like misinformation and toxicity in LLMs, which is important for users and developers, but it is incremental as it builds on existing self-correction research.
The study investigated whether self-correction capabilities in Large Language Models (LLMs) can improve trustworthiness, focusing on truthfulness and toxicity, and found that self-correction leads to improvements in these areas, though the extent varies by task and aspect.
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of misinformation and toxicity. Recent research has explored the self-correction capabilities of LLMs to enhance their performance. In this work, we investigate whether these self-correction capabilities can be harnessed to improve the trustworthiness of LLMs. We conduct experiments focusing on two key aspects of trustworthiness: truthfulness and toxicity. Our findings reveal that self-correction can lead to improvements in toxicity and truthfulness, but the extent of these improvements varies depending on the specific aspect of trustworthiness and the nature of the task. Interestingly, our study also uncovers instances of "self-doubt" in LLMs during the self-correction process, introducing a new set of challenges that need to be addressed.