Internalized Self-Correction for Large Language Models
This addresses the issue of hallucinations and errors in LLMs for users relying on accurate text generation, though it appears incremental as it builds on existing self-reflection techniques.
The paper tackles the problem of improving large language models (LLMs) by introducing Internalized Self-Correction (InSeC), a method that incorporates mistakes and corrections during training to enhance self-correction capabilities, resulting in improved instruction following and reduced hallucinations.
In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from negative sampling, self-reflection during training, and inference time. InSeC allows LLMs to correct themselves by introducing mistakes and their corresponding corrections during training, thereby converting the learning process into a true supervised learning task with both positive and negative examples. This approach can be extended to improve instruction following and correct hallucinations or incorrect sentences generated by LLMs.