mlsanityData to 14 Oct 2026

Improving Zero-shot LLM Re-Ranker with Risk Minimization

arXiv 2406.13331 ↗First posted 19 Jun 2024cs.CLcited by 3

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

In the Retrieval-Augmented Generation (RAG) system, advanced Large Language Models (LLMs) have emerged as effective Query Likelihood Models (QLMs) in an unsupervised way, which re-rank documents based on the probability of generating the query given the content of a document. However, directly prompting LLMs to approximate QLMs inherently is biased, where the estimated distribution might diverge from the actual document-specific distribution. In this study, we introduce a novel framework, UR3, which leverages Bayesian decision theory to both quantify and mitigate this estimation bias. Specifically, UR3 reformulates the problem as maximizing the probability of document generation, thereby harmonizing the optimization of query and document generation probabilities under a unified risk minimization objective. Our empirical results indicate that UR3 significantly enhances re-ranking, particularly in improving the Top-1 accuracy. It benefits the QA tasks by achieving higher accuracy with fewer input documents.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 37 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

19 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023In-Context Retrieval-Augmented Language Models31 Jan

Other references · 18

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  6. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  8. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  10. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  11. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  12. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
6 more
  1. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  2. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
  3. 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
  4. 2022Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Datacited by 61
  5. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  6. 2023Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-rankercited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Informationcited by 6
  2. 2025Structure-Augmented Reasoning Generationcited by 2
  3. 2026Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems
  2. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
  3. 2025Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems
  4. 2025LLM Optimization Unlocks Real-Time Pairwise Reranking
  5. 2025LLM-Independent Adaptive RAG: Let the Question Speak for Itself
  6. 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
  7. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  8. 2026CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation