mlsanityData to 14 Oct 2026

GenerationPrograms: Fine-grained Attribution with Executable Programs

arXiv 2506.14580 ↗First posted 17 Jun 2025cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent large language models (LLMs) achieve impressive performance in source-conditioned text generation but often fail to correctly provide fine-grained attributions for their outputs, undermining verifiability and trust. Moreover, existing attribution methods do not explain how and why models leverage the provided source documents to generate their final responses, limiting interpretability. To overcome these challenges, we introduce a modular generation framework, GenerationPrograms, inspired by recent advancements in executable "code agent" architectures. Unlike conventional generation methods that simultaneously generate outputs and attributions or rely on post-hoc attribution, GenerationPrograms decomposes the process into two distinct stages: first, creating an executable program plan composed of modular text operations (such as paraphrasing, compression, and fusion) explicitly tailored to the query, and second, executing these operations following the program's specified instructions to produce the final response. Empirical evaluations demonstrate that GenerationPrograms significantly improves attribution quality at both the document level and sentence level across two long-form question-answering tasks and a multi-document summarization task. We further demonstrate that GenerationPrograms can effectively function as a post-hoc attribution method, outperforming traditional techniques in recovering accurate attributions. In addition, the interpretable programs generated by GenerationPrograms enable localized refinement through modular-level improvements that further enhance overall attribution quality.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 53 of its 69 references that are in the map. First posted on arXiv 17 Jun 2025.

Builds on

53 of 69 references.

References · 53

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  10. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  11. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  12. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
38 more
  1. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  2. 2023Benchmarking Large Language Models for News Summarizationcited by 445
  3. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  4. 2023Augmented Language Models: a Surveycited by 403
  5. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  6. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  7. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  8. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  9. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  10. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  11. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  12. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
  13. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  14. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  15. 2018Ranking Sentences for Extractive Summarization with Reinforcement Learningcited by 128
  16. 2016Neural Summarization by Extracting Sentences and Wordscited by 116
  17. 2021Decontextualization: Making Sentences Stand-Alonecited by 102
  18. 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
  19. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  20. 2024Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systemscited by 87
  21. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  22. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 81
  23. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 79
  24. 2023Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarizationcited by 69
  25. 2023Extractive Summarization via ChatGPT for Faithful Summary Generationcited by 59
  26. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  27. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  28. 2023Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articlescited by 45
  29. 2021Exploring Neural Models for Query-Focused Summarizationcited by 44
  30. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 44
  31. 2019Scoring Sentence Singletons and Pairs for Abstractive Summarizationcited by 34
  32. 2024Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answeringcited by 25
  33. 2024Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generationcited by 25
  34. 2024On Positional Bias of Faithfulness for Long-form Summarizationcited by 22
  35. 2020Understanding Points of Correspondence between Sentences for Abstractive Summarizationcited by 16
  36. 2021Proposition-Level Clustering for Multi-Document Summarizationcited by 14
  37. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  38. 2022MACSum: Controllable Summarization with Mixed Attributescited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agentscited by 12
  2. 2026ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agentscited by 3
  3. 2026Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Executioncited by 2
  4. 2026Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarizationcited by 2