# FIRST: Faster Improved Listwise Reranking with Single Token Decoding

arXiv: https://arxiv.org/abs/2406.15657 · HTML: https://mlsanity.com/paper/2406.15657/

## Key facts

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

## Built on by (most cited first, 30 of 54)

- [CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking](https://mlsanity.com/paper/2412.01007/) (2024)
- [Improving LLM-as-a-Judge Inference with the Judgment Distribution](https://mlsanity.com/paper/2503.03064/) (2025)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking](https://mlsanity.com/paper/2506.09944/) (2025)
- [jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking](https://mlsanity.com/paper/2509.25085/) (2025)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)
- [DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.07233/) (2025)
- [LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking](https://mlsanity.com/paper/2504.07439/) (2025)
- [Controlled Retrieval-augmented Context Evaluation for Long-form RAG](https://mlsanity.com/paper/2506.20051/) (2025)
- [InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering](https://mlsanity.com/paper/2509.12765/) (2025)
- [Scalable In-context Ranking with Generative Models](https://mlsanity.com/paper/2510.05396/) (2025)
- [Self-Calibrated Listwise Reranking with Large Language Models](https://mlsanity.com/paper/2411.04602/) (2024)
- [Inference Scaling for Bridging Retrieval and Augmented Generation](https://mlsanity.com/paper/2412.10684/) (2024)
- [Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information](https://mlsanity.com/paper/2506.10859/) (2025)
- [CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval](https://mlsanity.com/paper/2505.13757/) (2025)
- [Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization](https://mlsanity.com/paper/2601.12078/) (2026)
- [An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking](https://mlsanity.com/paper/2411.05508/) (2024)
- [mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.24073/) (2025)
- [How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models](https://mlsanity.com/paper/2508.16757/) (2025)
- [LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval](https://mlsanity.com/paper/2510.13217/) (2025)
- [E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search](https://mlsanity.com/paper/2510.22733/) (2025)
- [Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration](https://mlsanity.com/paper/2604.10150/) (2026)
- [Reinforcement Speculative Decoding for Fast Ranking](https://mlsanity.com/paper/2505.20316/) (2025)
- [GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs](https://mlsanity.com/paper/2511.11653/) (2025)
- [RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking](https://mlsanity.com/paper/2601.07449/) (2026)
- [Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents](https://mlsanity.com/paper/2609.01642/) (2026)
- [Aligning Extraction and Generation for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04789/) (2025)
- [LANCER: LLM Reranking for Nugget Coverage](https://mlsanity.com/paper/2601.22008/) (2026)
- [The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs](https://mlsanity.com/paper/2605.08737/) (2026)
- [Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations](https://mlsanity.com/paper/2506.20294/) (2025)

## 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.