MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers
This work addresses ranking inefficiencies in LLM-based systems for information retrieval, though it appears incremental as it builds on existing pointwise rankers.
The paper tackled the problem of pointwise LLM rankers lacking standardized guidance and comprehensive evaluation by proposing a method that generates diverse criteria on-the-fly to improve ranking scores, resulting in marked performance enhancements on eight BEIR benchmark datasets.
The most recent pointwise Large Language Model (LLM) rankers have achieved remarkable ranking results. However, these rankers are hindered by two major drawbacks: (1) they fail to follow a standardized comparison guidance during the ranking process, and (2) they struggle with comprehensive considerations when dealing with complicated passages. To address these shortcomings, we propose to build a ranker that generates ranking scores based on a set of criteria from various perspectives. These criteria are intended to direct each perspective in providing a distinct yet synergistic evaluation. Our research, which examines eight datasets from the BEIR benchmark demonstrates that incorporating this multi-perspective criteria ensemble approach markedly enhanced the performance of pointwise LLM rankers.