Ext2Gen: Alignment through Unified Extraction and Generation for Robust Retrieval-Augmented Generation

ACL ARR 2025 February Submission808 Authors

Abstract: Retrieval-augmented generation (RAG) enhances LLMs by integrating external knowledge, but generation remains fragile due to the uncertain placement of relevant chunks and retrieval-induced information overload, leading to hallucinations. We propose Ext2Gen, a novel extract-then-generate model that enhances RAG robustness by first extracting query-relevant sentences before generating answers. To optimize this model, we employ preference alignment through pairwise feedback learning, enabling the model to generate robust answers regardless of variations in retrieval results. Extensive experiments demonstrate that Ext2Gen effectively identifies query-relevant sentences with high precision and recall, leading to highly reliable answers. Furthermore, deploying our model in a RAG environment reveals that it not only boosts the performance of the base LLM but also synergizes with advanced retrieval strategies like query expansion. The dataset and model will be available upon acceptance. A portion of the dataset is available beforehand at https://bit.ly/4b2gSzc.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: rag, robustness, alignment, qa

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: english

Submission Number: 808