SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs
This work addresses the need for specialized benchmarks to assess reranker performance in scientific RAG-LLMs, offering guidance for future development in this domain.
The authors tackled the problem of evaluating rerankers in retrieval-augmented generated LLMs for scientific literature question answering by introducing SciRerankBench, a benchmark spanning five scientific subjects with three types of question-context-answer pairs, and they systematically evaluated 13 rerankers on five LLM families to provide detailed insights into their performance.
Scientific literature question answering is a pivotal step towards new scientific discoveries. Recently, \textit{two-stage} retrieval-augmented generated large language models (RAG-LLMs) have shown impressive advancements in this domain. Such a two-stage framework, especially the second stage (reranker), is particularly essential in the scientific domain, where subtle differences in terminology may have a greatly negative impact on the final factual-oriented or knowledge-intensive answers. Despite this significant progress, the potential and limitations of these works remain unexplored. In this work, we present a Scientific Rerank-oriented RAG Benchmark (SciRerankBench), for evaluating rerankers within RAG-LLMs systems, spanning five scientific subjects. To rigorously assess the reranker performance in terms of noise resilience, relevance disambiguation, and factual consistency, we develop three types of question-context-answer (Q-C-A) pairs, i.e., Noisy Contexts (NC), Semantically Similar but Logically Irrelevant Contexts (SSLI), and Counterfactual Contexts (CC). Through systematic evaluation of 13 widely used rerankers on five families of LLMs, we provide detailed insights into their relative strengths and limitations. To the best of our knowledge, SciRerankBench is the first benchmark specifically developed to evaluate rerankers within RAG-LLMs, which provides valuable observations and guidance for their future development.