mlsanityData to 7 Oct 2026

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards

arXiv 2505.04847 ↗First posted 7 May 2025cs.CL cs.AIcited by 19

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupported information or contradictions even when provided with relevant context. This paper presents two complementary efforts at Vectara to measure and benchmark LLM faithfulness in RAG. First, we describe our original hallucination leaderboard, which has tracked hallucination rates for LLMs since 2023 using our HHEM hallucination detection model. Motivated by limitations observed in current hallucination detection methods, we introduce FaithJudge, an LLM-as-a-judge framework that leverages a pool of diverse human-annotated hallucination examples to substantially improve the automated hallucination evaluation of LLMs. We introduce an enhanced hallucination leaderboard centered on FaithJudge that benchmarks LLMs on RAG faithfulness in summarization, question-answering, and data-to-text generation tasks. FaithJudge enables a more reliable benchmarking of LLM hallucinations in RAG and supports the development of more trustworthy generative AI systems: https://github.com/vectara/FaithJudge.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 35 of its 50 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

35 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models31 Dec

Other references · 34

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  10. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  11. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  12. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
22 more
  1. 2015Teaching Machines to Read and Comprehendcited by 1,039
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2020SummEval: Re-evaluating Summarization Evaluationcited by 666
  4. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  5. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  6. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
  7. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
  8. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  9. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 233
  10. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  11. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  12. 2023Large language models can accurately predict searcher preferencescited by 129
  13. 2023Human-like Summarization Evaluation with ChatGPTcited by 126
  14. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
  15. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  16. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 82
  17. 2023MeetingBank: A Benchmark Dataset for Meeting Summarizationcited by 81
  18. 2023ChatGPT as a Factual Inconsistency Evaluator for Text Summarizationcited by 75
  19. 2024TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarizationcited by 66
  20. 2020What Have We Achieved on Text Summarization?cited by 65
  21. 2025The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Inputcited by 49
  22. 2023Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Modelcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 14.

19 papers.

Sort:

By area:

  1. 2025Kimi K2: Open Agentic Intelligencecited by 523
  2. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  3. 2025Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoderscited by 6
  4. 2026MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucinationcited by 5
  5. 2025Structured Prompts Improve Evaluation of Language Modelscited by 3
  6. 2026PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Qualitycited by 3
  7. 2025Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Surveycited by 2
  8. 2026PrivacyAlign: Contextual Privacy Alignment for LLM Agentscited by 2
  9. 2026GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMscited by 1
  10. 2026LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messagingcited by 0
  11. 2026Summarization is Not Dead Yetcited by 0
  12. 2026BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigationcited by 0
7 more
  1. 2026Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AIcited by 0
  2. 2026A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facilitycited by 0
  3. 2026GuidedRAG: Semantic Steering of Retrieval-Augmented Generationcited by 0
  4. 2026SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systemscited by 0
  5. 2026Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generationcited by 0
  6. 2026AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Researchcited by 0
  7. 2026RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
  2. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  3. 2026Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
  4. 2024A review of faithfulness metrics for hallucination assessment in Large Language Models
  5. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generation
  6. 2025Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
  7. 2024Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders
  8. 2026Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey