MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model
This work addresses the issue of hallucinations and outdated information in large language models for question answering, though it appears incremental as it builds on existing learning-to-rank methods.
The paper tackles the problem of improving question answering retrieval systems by proposing a multi-result ranking model that combines heterogeneous information retrieval techniques, achieving state-of-the-art results on the ReQA SQuAD benchmark.
Large Language Models (LLMs) often struggle with hallucinations and outdated information. To address this, Information Retrieval (IR) systems can be employed to augment LLMs with up-to-date knowledge. However, existing IR techniques contain deficiencies, posing a performance bottleneck. Given the extensive array of IR systems, combining diverse approaches presents a viable strategy. Nevertheless, prior attempts have yielded restricted efficacy. In this work, we propose an approach that leverages learning-to-rank techniques to combine heterogeneous IR systems. We demonstrate the method on two Retrieval Question Answering (ReQA) tasks. Our empirical findings exhibit a significant performance enhancement, outperforming previous approaches and achieving state-of-the-art results on ReQA SQuAD.