Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
This addresses factuality concerns in knowledge-intensive tasks for users relying on LLMs, though it is incremental as it builds on existing Chain-of-Thought prompting.
The paper tackles the problem of factual correctness in large language models by proposing a Verify-and-Edit framework that post-edits reasoning chains using external knowledge, leading to accuracy improvements in open-domain question-answering tasks.
As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness. Generating unfactual texts not only leads to lower performances but also degrades the trust and validity of their applications. Chain-of-Thought (CoT) prompting improves trust and model performance on complex reasoning tasks by generating interpretable reasoning chains, but still suffers from factuality concerns in knowledge-intensive tasks. In this paper, we propose the Verify-and-Edit framework for CoT prompting, which seeks to increase prediction factuality by post-editing reasoning chains according to external knowledge. Building on top of GPT-3, our framework lead to accuracy improvements in multiple open-domain question-answering tasks.