RAC: Efficient LLM Factuality Correction with Retrieval Augmentation
This addresses the issue of unreliable factual outputs from LLMs for users in NLP applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of factual inaccuracies in Large Language Models (LLMs) by introducing Retrieval Augmented Correction (RAC), a low-latency post-correction method that improves factual performance by up to 30% over state-of-the-art baselines on two evaluation datasets.
Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency post-correction method, \textbf{Retrieval Augmented Correction (RAC)}, aimed at enhancing the factual performance of LLMs without requiring additional fine-tuning. Our method is general and can be used with any instruction-tuned LLM, and has greatly reduced latency compared to prior approaches. RAC decomposes the LLM's output into atomic facts and applies a fine-grained verification and correction process with retrieved content to verify and correct the LLM-generated output. Our extensive experiments show that RAC yields up to 30\% improvements over state-of-the-art baselines across two popular factuality evaluation datasets, validating its efficacy and robustness in both with and without the integration of Retrieval-Augmented Generation (RAG) across different LLMs.\footnote{Our code is at \url{https://github.com/jlab-nlp/Retrieval-Augmented-Correction}}