REFO: Reinforced Evolutionary Faithfulness Optimization for Large Language Models

Despite its success in enriching LLMs with external knowledge, RAG remains plagued by faithfulness hallucinations, where generated text contradicts the retrieved source information. Previous research on faithfulness hallucination in LLMs is frequently hindered by prohibitive manual annotation costs and a dependency on static datasets, which caps their performance and adaptability. Furthermore, these models lack a clear training mechanism to explicitly promote contextual focus. In this work, we propose a novel iterative self-evolution framework to enhance model faithfulness. This framework autonomously generates high-quality data and leverages it for the continuous self-optimization of the model, leading to significant improvements in faithfulness. Our experimental analysis reveals that improving model faithfulness encourages a closer alignment of the attention distribution with the given context. Based on this finding, we design an attention-based loss function to further promote this process. Experimental results show that our model achieves state-of-the-art faithfulness on a range of context-based question-answering datasets, marking a significant advancement over previous approaches.