InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking

• URL: http://arxiv.org/abs/2506.14086v1
• Date: Tue, 17 Jun 2025 01:04:45 GMT
• Title: InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
• Authors: Rahul Seetharaman, Kaustubh D. Dhole, Aman Bansal,
• Abstract summary: InsertRank is an LLM-based reranker that leverages lexical signals like BM25 scores during reranking to further improve retrieval performance.<n>With Deepseek-R1, InsertRank achieves a score of 37.5 on the BRIGHT benchmark, and 51.1 on the R2MED benchmark, surpassing previous methods.
• Score: 3.1125398490785217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated significant strides across various information retrieval tasks, particularly as rerankers, owing to their strong generalization and knowledge-transfer capabilities acquired from extensive pretraining. In parallel, the rise of LLM-based chat interfaces has raised user expectations, encouraging users to pose more complex queries that necessitate retrieval by ``reasoning'' over documents rather than through simple keyword matching or semantic similarity. While some recent efforts have exploited reasoning abilities of LLMs for reranking such queries, considerable potential for improvement remains. In that regards, we introduce InsertRank, an LLM-based reranker that leverages lexical signals like BM25 scores during reranking to further improve retrieval performance. InsertRank demonstrates improved retrieval effectiveness on -- BRIGHT, a reasoning benchmark spanning 12 diverse domains, and R2MED, a specialized medical reasoning retrieval benchmark spanning 8 different tasks. We conduct an exhaustive evaluation and several ablation studies and demonstrate that InsertRank consistently improves retrieval effectiveness across multiple families of LLMs, including GPT, Gemini, and Deepseek models. %In addition, we also conduct ablation studies on normalization by varying the scale of the BM25 scores, and positional bias by shuffling the order of the documents. With Deepseek-R1, InsertRank achieves a score of 37.5 on the BRIGHT benchmark. and 51.1 on the R2MED benchmark, surpassing previous methods.

Related papers

• Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion [0.0]
  Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion.<n>We introduce a novel fusion ranking framework, Exp4Fuse, which enhances the performance of sparse retrievers.
  arXiv  Detail & Related papers  (2025-06-05T08:44:34Z)
• Likert or Not: LLM Absolute Relevance Judgments on Fine-Grained Ordinal Scales [3.4068099825211986]
  Two most common prompts to elicit relevance judgments are pointwise scoring and listwise ranking.<n>The current research community consensus is that listwise ranking yields superior performance.<n>In tension with this hypothesis, we find that the gap between pointwise scoring and listwise ranking shrinks when pointwise scoring is implemented using a sufficiently large ordinal relevance label space.
  arXiv  Detail & Related papers  (2025-05-25T21:41:35Z)
• Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning [76.50690734636477]
  We introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task.<n>Our experiments on the TREC DL and BRIGHT datasets show that Rank-R1 is highly effective, especially for complex queries.
  arXiv  Detail & Related papers  (2025-03-08T03:14:26Z)
• Self-Calibrated Listwise Reranking with Large Language Models [137.6557607279876]
  Large language models (LLMs) have been employed in reranking tasks through a sequence-to-sequence approach. This reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. We propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking.
  arXiv  Detail & Related papers  (2024-11-07T10:31:31Z)
• LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering [0.0]
  We propose LoRE, a novel approach that improves answer accuracy and relevance by mitigating positional bias. LoRE employs an ensemble of diverse retrievers, such as BM25 and sentence transformers with FAISS indexing. A key innovation is a logit-based answer ranking algorithm that combines the logit scores from a large language model with the retrieval ranks of the passages.
  arXiv  Detail & Related papers  (2024-10-13T23:06:08Z)
• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)
• SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs [85.54906813106683]
  We propose a simple yet effective framework to enhance open-domain question answering (ODQA) with large language models (LLMs) SuRe helps LLMs predict more accurate answers for a given question, which are well-supported by the summarized retrieval (SuRe) Experimental results on diverse ODQA benchmarks demonstrate the superiority of SuRe, with improvements of up to 4.6% in exact match (EM) and 4.0% in F1 score over standard prompting approaches.
  arXiv  Detail & Related papers  (2024-04-17T01:15:54Z)
• Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting [65.00288634420812]
  Pairwise Ranking Prompting (PRP) is a technique to significantly reduce the burden on Large Language Models (LLMs) Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs.
  arXiv  Detail & Related papers  (2023-06-30T11:32:25Z)
• Zero-Shot Listwise Document Reranking with a Large Language Model [58.64141622176841]
  We propose Listwise Reranker with a Large Language Model (LRL), which achieves strong reranking effectiveness without using any task-specific training data. Experiments on three TREC web search datasets demonstrate that LRL not only outperforms zero-shot pointwise methods when reranking first-stage retrieval results, but can also act as a final-stage reranker.
  arXiv  Detail & Related papers  (2023-05-03T14:45:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.