{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/attribute-first-then-generate-locally","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","arxiv_id":"2403.17104","date":"2024-03-25","proceeding":null,"authors":["Aviv Slobodkin","Eran Hirsch","Arie Cattan","Tal Schuster","Ido Dagan"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2403.17104v3","url_pdf":"https://arxiv.org/pdf/2403.17104v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"attribute-first-then-generate-locally","repo_url":"https://github.com/lovodkin93/attribute-first-then-generate","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"fact-verification","task_name":"Fact Verification"},{"task_slug":"long-form-question-answering","task_name":"Long Form Question Answering"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.17104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17104"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lovodkin93/attribute-first-then-generate","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bfd87fc3b9956bb7","entry":"load_data","repo":"lovodkin93/attribute-first-then-generate","repo_kind":"official","path":"fine_tuned/inference.py","file_url":"https://github.com/lovodkin93/attribute-first-then-generate/blob/HEAD/fine_tuned/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfd87fc3b9956bb7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}