mlsanityData to 7 Oct 2026

Attribute First, then Generate: Locally-attributable Grounded Text Generation

arXiv 2403.17104 ↗First posted 25 Mar 2024cs.CLcited by 54

Not on the map. Why?

Abstract (arXiv)

Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named "Attribute First, then Generate", breaks down the conventional end-to-end generation process into three intuitive steps: content selection, sentence planning, and sequential sentence generation. By initially identifying relevant source segments ("select first") and then conditioning the generation process on them ("then generate"), we ensure these segments also act as the output's fine-grained attributions ("select" becomes "attribute"). Tested on Multi-document Summarization and Long-form Question-answering, our method not only yields more concise citations than the baselines but also maintains - and in some cases enhances - both generation quality and attribution accuracy. Furthermore, it significantly reduces the time required for fact verification by human assessors.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

36 of 64 references.

References · 36

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  6. 2020SummEval: Re-evaluating Summarization Evaluationcited by 666
  7. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  9. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  10. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  11. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  12. 2022Teaching language models to support answers with verified quotescited by 290
24 more
  1. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  2. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  3. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  4. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  5. 2018Bottom-Up Abstractive Summarizationcited by 177
  6. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  7. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 146
  8. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  9. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  10. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 82
  11. 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
  12. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  13. 2022Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metricscited by 37
  14. 2019Controlled Crowdsourcing for High-Quality QA-SRL Annotationcited by 34
  15. 2021Programming Puzzlescited by 25
  16. 2019Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarizationcited by 22
  17. 2020Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baselinecited by 22
  18. 2019Analyzing Sentence Fusion in Abstractive Summarizationcited by 19
  19. 2023SEMQA: Semi-Extractive Multi-Source Question Answeringcited by 19
  20. 2020Learning to Fuse Sentences with Transformers for Summarizationcited by 14
  21. 2023Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concretenesscited by 13
  22. 2022Controlled Text Reductioncited by 10
  23. 2023Revisiting Sentence Union Generation as a Testbed for Text Consolidationcited by 6
  24. 2023A Novel Computational and Modeling Foundation for Automatic Coherence Assessmentcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 25; 2026: 15.

54 papers.

Sort:

By area:

  1. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  2. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 78
  3. 2024Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refusecited by 33
  4. 2024RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignmentcited by 22
  5. 2025Ai2 Scholar QA: Organized Literature Synthesis with Attributioncited by 22
  6. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMscited by 21
  7. 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Modelscited by 19
  8. 2024Correctness is not Faithfulness in RAG Attributionscited by 18
  9. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domaincited by 16
  10. 2024ALiiCE: Evaluating Positional Fine-grained Citation Generationcited by 15
  11. 2024Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citationscited by 15
  12. 2025TokenShapley: Token Level Context Attribution with Shapley Valuecited by 14
38 more
  1. 2024Verifiable by Design: Aligning Language Models to Quote from Pre-Training Datacited by 13
  2. 2024Localizing Factual Inconsistencies in Attributable Text Generationcited by 13
  3. 2025LAQuer: Localized Attribution Queries in Content-grounded Generationcited by 13
  4. 2024CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularitycited by 12
  5. 2025Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generationcited by 12
  6. 2026Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agentscited by 10
  7. 2024The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generationscited by 8
  8. 2025Lessons from Training Grounded LLMs with Verifiable Rewardscited by 8
  9. 2025Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Modelscited by 7
  10. 2025Principled Context Engineering for RAG: Statistical Guarantees via Conformal Predictioncited by 6
  11. 2024Citekit: A Modular Toolkit for Large Language Model Citation Generationcited by 5
  12. 2024Attention with Dependency Parsing Augmentation for Fine-Grained Attributioncited by 5
  13. 2025Large Language Model Sourcing: A Surveycited by 5
  14. 2025TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classificationcited by 4
  15. 2025GenerationPrograms: Fine-grained Attribution with Executable Programscited by 4
  16. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasetscited by 4
  17. 2025MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answeringcited by 3
  18. 2026Diagnosing and Repairing Citation Failures in Generative Engine Optimizationcited by 3
  19. 2025On Synthesizing Data for Context Attribution in Question Answeringcited by 2
  20. 2025A Large-Language-Model Framework for Automated Humanitarian Situation Reportingcited by 2
  21. 2026GenProve: Learning to Generate Text with Fine-Grained Provenancecited by 2
  22. 2026Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarizationcited by 2
  23. 2024DoubleDipper: Improving Long-Context LLMs via Context Recyclingcited by 1
  24. 2025MCiteBench: A Multimodal Benchmark for Generating Text with Citationscited by 1
  25. 2025Can one size fit all?: Measuring Failure in Multi-Document Summarization Domain Transfercited by 1
  26. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 1
  27. 2025A Unifying Scheme for Extractive Content Selection Taskscited by 1
  28. 2026Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScorecited by 1
  29. 2026User-Centric Evidence Ranking for Attribution and Fact Verificationcited by 1
  30. 2026CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answeringcited by 1
  31. 2025LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Reviewcited by 0
  32. 2025Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokenscited by 0
  33. 2025Citation Failure: Definition, Analysis and Efficient Mitigationcited by 0
  34. 2026MAPLE: Medical Aspect-Based Summarization with Phrase-Level Evidencecited by 0
  35. 2026eTracer: Polarity-Aware Evidence Groundingcited by 0
  36. 2025C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Modelscited by 0
  37. 2026AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarizationcited by 0
  38. 2026Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructscited by 0

50 most cited of 54 All 54 (JSON)