LLM Reranking

LLM: Large Language Model

Overview

LLM reranking studies how to reorder a shortlist of documents, products, answers, or tools so that the most useful candidates appear first, often improving retrieval-augmented generation and recommendations. Common approaches ask models to score items individually, compare them in pairs or lists, or reason over evidence; other methods fine-tune or distill smaller rerankers, calibrate attention scores, or use reinforcement learning. Evaluations include TREC and BEIR retrieval benchmarks as well as scientific, conversational-memory, recommendation, and domain-specific tasks, increasingly measuring downstream answer quality and efficiency alongside ranking metrics. Key tensions are inference cost and sensitivity to candidate order, prompts, and bias, while reranking cannot recover relevant items missing from the initial retrieval pool and topical relevance may not match downstream usefulness.

Latest papers

CardsList

144 papers15 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

  1. Deal With It: On Better Schedules for Listwise Reranking

    Nov 17, 2026Benjamin Clavié, Herumb Shandilya, Hanna Lichtenberg +2LLM Inference SchedulingLLM Reranking

  2. Evidence Diet: When Graph Evidence Helps LLMs Rank Competing Candidates

    Nov 16, 2026Yuchong Hu, Zhao Zhang, Ziyao Zhao +2Large Language Model-Based RecommendationLLM Reranking

  3. Every Clause Counts: Instruction-Following Reranking by Multiplying Small, Answerable Questions

    Nov 2, 2026S. M. Mahbub Uddin Ahmed, Abdullah Al MusaddiqLLM Reranking

  4. Re3^3Rank: Listwise Reranking with Reasoning-Conditioned Retrieval Heads

    Nov 2, 2026Ruiyi Yan, Zhuoyuan Mao, Yugo Murawaki +1Learning to RankLLM Reranking

  5. An auditable agentic pipeline for variant-to-gene prioritisation, validated against orthogonal functional evidence

    Nov 1, 2026Shakuntala Baichoo, Sohail, Sarkar +1BioinformaticsGenomics

  6. On the Limits of Test-Time Compute for Self-Evaluation

    Oct 30, 2026Anirudh Buvanesh, Khaled Rouissi, Sujin Yun +6Language Model Self-AssessmentLanguage Model Self-Verification

  7. DecisionRank: On-Policy Distillation for Decision-Model Rerankers

    Oct 30, 2026Yanran Wu, Dian Yu, Chongyang Bai +10Learning to RankLLM Reranking

  8. Glance: The Generator Is Its Own Reranker

    Oct 29, 2026Adilet Metinov, Chingiz ArzievLLM RerankingRetrieval-Augmented Generation

  9. Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback

    Oct 28, 2026Quan Mai, Susan Gauch, Gibson NkhataRank AggregationLLM Reranking

  10. Nothing Left Behind: Embedding Retrieval and Language Model Screening for High Recall Evidence Search

    Oct 27, 2026Giuliano Martinelli, Abelardo Carlos Martinez Lorenzo, Satvik Garg +4Evidence RetrievalInformation Retrieval

  11. Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation

    Oct 26, 2026Haocheng Mei, Yuchuan Tian, Ye Yuan +5LLM RerankingLearning to Rank

  12. Can System-1-Style Decision Models Replace Dedicated Rerankers in RAG? A Systems Evaluation

    Oct 26, 2026Qiaomu Li, Ying XieLLM RerankingRAG Evaluation

  13. SKALOS: Learning to Distinguish Similar Skills with Capability Graphs

    Oct 26, 2026Wenhan Xiao, Ziwei Zhang, Xingcheng Fu +5LLM Agent Skill RetrievalTool Selection for Language Model Agents

  14. System One models Are Not Better Rerankers

    Oct 23, 2026Michael Dinzinger, Kanishka Ghosh Dastidar, Michael GranitzerLLM RerankingInformation Retrieval

  15. Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval

    Oct 17, 2026Yunhan Li, Mingjie Xie, Zeyang Shi +2LLM RerankingLegal IR

  16. Reasoning Reranking with Semantic IDs as the Sole Item Representation

    Oct 16, 2026Zhenwei Tang, Jintao Liu, Di Bai +2LLM RerankingSemantic ID Recommendation

  17. Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search

    Oct 8, 2026Jimmy Lin, Sahel Sharifymoghaddam, Lingwei Gu +1LLM RerankingLearning to Rank

  18. SkillContrast: Difference-Guided Text Selection for Agent Skill Reranking

    Oct 8, 2026Jiandong Ding, Honglei Ji, Ming Liu +1LLM Agent Skill RetrievalLLM Reranking

  19. Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching

    Oct 7, 2026Runze Li, Hanchen Wang, Ying Zhang +1Semantic MappingLLM Reranking

  20. OTel: Open Telco AI Datasets, Benchmarks, and Models

    Oct 6, 2026Farbod Tavakkoli, Gregory Diamos, Kenneth Church +10Language Model Post-TrainingLLM Reranking

  21. Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering

    Sep 29, 2026Bhagyesh Rathi, Eshan Chawla, William B. AndreopoulosLate Interaction RetrievalScientific QA

  22. Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models

    Sep 28, 2026Qiyao Ma, Junshan Zhang, Zhe ZhaoLearning to RankLLM Reranking

  23. Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference

    Sep 27, 2026Yilong Li, Chengpo Yan, Aayan Arish +1LLM EvaluationLLM Answer Verification