mlsanityData to 14 Oct 2026

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

arXiv 2406.15657 ↗First posted 21 Jun 2024cs.IRcited by 54

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised approaches. However, conventional listwise LLM reranking methods lack efficiency as they provide ranking output in the form of a generated ordered sequence of candidate passage identifiers. Further, they are trained with the typical language modeling objective, which treats all ranking errors uniformly--potentially at the cost of misranking highly relevant passages. Addressing these limitations, 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. Further, we incorporate a learning-to-rank loss during training, prioritizing ranking accuracy for the more relevant passages. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Finally, to illustrate the practical effectiveness of listwise LLM rerankers, we investigate their application in providing relevance feedback for retrievers during inference. 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.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Jun 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 28; 2026: 22.

54 papers.

Sort:

By area:

  1. 2024CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Rerankingcited by 37
  2. 2025Improving LLM-as-a-Judge Inference with the Judgment Distributioncited by 37
  3. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  4. 2025Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingcited by 31
  5. 2025jina-reranker-v3: Last but Not Late Interaction for Listwise Document Rerankingcited by 24
  6. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  7. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generationcited by 15
  8. 2025LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Rerankingcited by 12
  9. 2025Controlled Retrieval-augmented Context Evaluation for Long-form RAGcited by 9
  10. 2025InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filteringcited by 8
  11. 2025Scalable In-context Ranking with Generative Modelscited by 8
  12. 2024Self-Calibrated Listwise Reranking with Large Language Modelscited by 7
38 more
  1. 2024Inference Scaling for Bridging Retrieval and Augmented Generationcited by 7
  2. 2025Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Informationcited by 6
  3. 2025CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrievalcited by 5
  4. 2026Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalizationcited by 5
  5. 2024An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Rerankingcited by 4
  6. 2025mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generationcited by 4
  7. 2025How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Modelscited by 4
  8. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4
  9. 2025E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Searchcited by 4
  10. 2026Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibrationcited by 4
  11. 2025Reinforcement Speculative Decoding for Fast Rankingcited by 3
  12. 2025GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMscited by 3
  13. 2026RLPO: Residual Listwise Preference Optimization for Long-Context Review Rankingcited by 3
  14. 2026Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agentscited by 3
  15. 2025Aligning Extraction and Generation for Robust Retrieval-Augmented Generationcited by 2
  16. 2026LANCER: LLM Reranking for Nugget Coveragecited by 2
  17. 2026The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputscited by 2
  18. 2025Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorationscited by 1
  19. 2025Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generationcited by 1
  20. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLMcited by 1
  21. 2025Token-Controlled Re-ranking for Sequential Recommendation via LLMscited by 1
  22. 2026Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoderscited by 1
  23. 2026An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fitcited by 1
  24. 2026Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learningcited by 1
  25. 2026GRISP: Guided Recurrent IRI Selection over SPARQL Skeletonscited by 1
  26. 2026Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrievalcited by 1
  27. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  28. 2026SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Searchcited by 1
  29. 2025TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEscited by 0
  30. 2025Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discoverycited by 0
  31. 2025Embedding-Based Context-Aware Rerankercited by 0
  32. 2025OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Explorationcited by 0
  33. 2025Charting the Design Space of Neural Graph Representations for Subgraph Matchingcited by 0
  34. 2026DualView: Adaptive Local-Global Fusion for Multi-Hop Document Rerankingcited by 0
  35. 2026CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoringcited by 0
  36. 2026PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalizationcited by 0
  37. 2026SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Trainingcited by 0
  38. 2026LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passagescited by 0

50 most cited of 54 All 54 (JSON)