mlsanityData to 14 Oct 2026

RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems

arXiv 2601.02917 ↗First posted 6 Jan 2026cs.CL cs.AIcited by 2

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Hallucination is a major concern in LLM-driven service systems, necessitating explicit knowledge grounding for compliance-guaranteed responses. In this paper, we introduce Retrieval-Augmented Learning-to-Match (RAL2M), a novel framework that eliminates generation hallucination by repositioning LLMs as query-response matching judges within a retrieval-based system, providing a robust alternative to purely generative approaches. To further mitigate judgment hallucination, we propose a query-adaptive latent ensemble strategy that explicitly models heterogeneous model competence and interdependencies among LLMs, deriving a calibrated consensus decision. Extensive experiments on large-scale benchmarks demonstrate that the proposed method effectively leverages the "wisdom of the crowd" and significantly outperforms strong baselines. Finally, we discuss best practices and promising directions for further exploiting latent representations in future work.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 62 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

34 of 62 references.

References · 34

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  5. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  6. 2022Mixture-of-Experts with Expert Choice Routingcited by 623
  7. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  8. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  9. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  10. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judgescited by 318
  11. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  12. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 117
22 more
  1. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  2. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
  3. 2015Convolutional Neural Network Architectures for Matching Natural Language Sentencescited by 82
  4. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  5. 2016Learning to Match Using Local and Distributed Representations of Text for Web Searchcited by 68
  6. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 56
  7. 2023EcoAssistant: Using LLM Assistant More Affordably and Accuratelycited by 49
  8. 2024LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversitycited by 42
  9. 2018Aggregated Momentum: Stability Through Passive Dampingcited by 36
  10. 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attentioncited by 32
  11. 2023Generative AI Text Classification using Ensemble LLM Approachescited by 29
  12. 2016Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNNcited by 27
  13. 2025Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Informationcited by 26
  14. 2025Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreementcited by 14
  15. 2015Early Inference in Energy-Based Models Approximates Back-Propagationcited by 13
  16. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  17. 2025A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classificationcited by 8
  18. 2025Semantic Agreement Enables Efficient Open-Ended LLM Cascadescited by 7
  19. 2025Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowdscited by 6
  20. 2024Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labelingcited by 5
  21. 2025QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluationcited by 5
  22. 2024Examining Independence in Ensemble Sentiment Analysis: A Study on the Limits of Large Language Models Using the Condorcet Jury Theoremcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discoverycited by 2
  2. 2026Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Frameworkcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  2. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
  3. 2025HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
  4. 2025Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search
  5. 2025QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
  6. 2024RAGged Edges: The Double-Edged Sword of Retrieval-Augmented Chatbots
  7. 2026No One Size Fits All: QueryBandits for Hallucination Mitigation
  8. 2025Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning