mlsanityData to 14 Oct 2026

Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study

arXiv 2404.07060 ↗First posted 10 Apr 2024cs.CL cs.LGcited by 7

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded, even when those sentences contain correct ground-truth answers. Additionally, we examine the impacts of factors such as model size, decoding strategy, and instruction tuning on groundedness. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations. This study provides novel insights into the groundedness challenges in LFQA and underscores the necessity for more robust mechanisms in LLMs to mitigate the generation of ungrounded content.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 42 of its 50 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

42 of 50 references.

References · 42

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  10. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  12. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
30 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  4. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
  5. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  6. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  7. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  9. 2019ELI5: Long Form Question Answeringcited by 575
  10. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  11. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  12. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  13. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  14. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 293
  15. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  16. 2022Prompting GPT-3 To Be Reliablecited by 260
  17. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  18. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  19. 2021Hurdles to Progress in Long-form Question Answeringcited by 167
  20. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
  21. 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
  22. 2023Do Language Models Know When They're Hallucinating References?cited by 116
  23. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  24. 2023SILO Language Models: Isolating Legal Risk In a Nonparametric Datastorecited by 71
  25. 2023A Survey of Large Language Models Attributioncited by 71
  26. 2022Read before Generate! Faithful Long Form Question Answering with Machine Readingcited by 47
  27. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 45
  28. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45
  29. 2023"According to ...": Prompting Language Models Improves Quoting from Pre-Training Datacited by 42
  30. 2022ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Datacited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2024Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recallcited by 32
  2. 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routingcited by 29
  3. 2025Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolutioncited by 7
  4. 2025From Millions of Tweets to Actionable Insights: Leveraging LLMs for User Profilingcited by 3
  5. 2026CUE-R: Beyond the Final Answer in Retrieval-Augmented Generationcited by 2
  6. 2026Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generationcited by 0
  7. 2026Structured State Reconciliation for Human-AI Task Handovercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering
  2. 2025Where is this coming from? Making groundedness count in the evaluation of Document VQA models
  3. 2024GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering
  4. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
  5. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
  6. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
  7. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
  8. 2025Evaluating the Retrieval Robustness of Large Language Models