mlsanityData to 7 Oct 2026

Citation Failure: Definition, Analysis and Efficient Mitigation

arXiv 2510.20303 ↗First posted 23 Oct 2025cs.CLcited by 0

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

Abstract (arXiv)

Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure, where a model generates a helpful response, but fails to generate citations to complete evidence. In contrast to previous work, we propose to disentangle this from response failure, where the response itself is flawed, and citing complete evidence is impossible. To address citation failure, this work follows a two-step approach: (1) We study when citation failure occurs and (2) how it can be mitigated efficiently. For step 1, we extend prior work by investigating how the relation between response and evidence affects citation quality. We introduce CITECONTROL, a benchmark that systematically varies this relation to enable the analysis of failure modes. Experiments show that failures increase with relational complexity and suggest that combining citation methods could improve performance, motivating step 2. To study the efficient improvement of LLM citation, we propose CITENTION, a framework integrating generative, attention-based, and retrieval-based methods. Results demonstrate substantial citation improvements on CITECONTROL and in transfer settings. We make our data and code publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 52 of its 70 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

52 of 70 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025NeoQA: Evidence-based Question Answering with Generated News Events9 May
  2. 2024Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation19 Jun
  3. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents16 Apr

Other references · 49

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  7. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  8. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  11. 2024Phi-4 Technical Reportcited by 675
  12. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
37 more
  1. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  2. 2021Efficient Attentions for Long Document Summarizationcited by 342
  3. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
  4. 2024LoRA Learns Less and Forgets Lesscited by 313
  5. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  6. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  7. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  8. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 116
  9. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  10. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 96
  11. 2024ContextCite: Attributing Model Generation to Contextcited by 93
  12. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 78
  13. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 55
  14. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  15. 2023An Open Source Data Contamination Report for Large Language Modelscited by 47
  16. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 42
  17. 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Reviewcited by 37
  18. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  19. 2025Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingcited by 30
  20. 2024RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Contentcited by 26
  21. 2024Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answeringcited by 25
  22. 2024Improving Attributed Text Generation of Large Language Models via Preference Learningcited by 23
  23. 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Modelscited by 19
  24. 2025GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluationcited by 18
  25. 2024Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphscited by 16
  26. 2025LAQuer: Localized Attribution Queries in Content-grounded Generationcited by 13
  27. 2024Learning Fine-Grained Grounded Citations for Attributed Large Language Modelscited by 12
  28. 2024Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decompositioncited by 12
  29. 2025Learning to Attribute with Attentioncited by 11
  30. 2024Attribute or Abstain: Large Language Models as Long Document Assistantscited by 10
  31. 2022TRUE: Re-evaluating Factual Consistency Evaluationcited by 7
  32. 2024Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcriptscited by 6
  33. 2024Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challengescited by 5
  34. 2024Attention with Dependency Parsing Augmentation for Fine-Grained Attributioncited by 5
  35. 2025Unstructured Evidence Attribution for Long Context Query Focused Summarizationcited by 5
  36. 2025TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classificationcited by 4
  37. 2025Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024On the Capacity of Citation Generation by Large Language Models
  2. 2025CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction
  3. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  4. 2026How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
  5. 2025Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution
  6. 2026Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
  7. 2026DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA
  8. 2026AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents