{"paper":{"title":"Generative Artificial Intelligence for Literature Reviews","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Generative AI can assist with literature reviews through summarization, question answering, and data extraction while requiring attention to risks.","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Gerit Wagner, Guy Pare, Julian Prester, Reza Mousavi, Roman Lukyanenko","submitted_at":"2026-05-15T15:42:54Z","abstract_excerpt":"Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public by storm. In particular, impressive GenAI capabilities such as summarization of large text corpora, question-answering, data extraction, and translation, carry profound implications for the conduct of literature reviews. This impacts science, organizations and the general public, as all can benefit from GenAI-supported literature reviews. Building on the technical foundations of GenAI and grounded in established methodological discourse, this wor"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Generative AI capabilities such as summarization of large text corpora, question-answering, data extraction, and translation carry profound implications for the conduct of literature reviews.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That illustrative prompts and suggested strategies remain methodologically sound when applied by typical users without introducing systematic biases, hallucinations, or incomplete coverage that would invalidate the resulting review.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Generative AI tools can assist literature reviews via summarization, extraction, and question-answering, with the paper providing prompt examples and balanced discussion of opportunities, risks, and open methodological issues.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Generative AI can assist with literature reviews through summarization, question answering, and data extraction while requiring attention to risks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"62a8aff54b1933cfe41ef8d82bd10f14f3107b629881329ebcdfcb1d0be18597"},"source":{"id":"2605.16475","kind":"arxiv","version":1},"verdict":{"id":"527069e4-6acd-4ab9-8018-defbc4ddba94","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:39:26.572967Z","strongest_claim":"Generative AI capabilities such as summarization of large text corpora, question-answering, data extraction, and translation carry profound implications for the conduct of literature reviews.","one_line_summary":"Generative AI tools can assist literature reviews via summarization, extraction, and question-answering, with the paper providing prompt examples and balanced discussion of opportunities, risks, and open methodological issues.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That illustrative prompts and suggested strategies remain methodologically sound when applied by typical users without introducing systematic biases, hallucinations, or incomplete coverage that would invalidate the resulting review.","pith_extraction_headline":"Generative AI can assist with literature reviews through summarization, question answering, and data extraction while requiring attention to risks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16475/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.265609Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:52:01.939142Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.114242Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.044244Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3c85f2fa503b402ffd9823aadf8ee96d5e30b7048b34ca64ce6fa19d6e48d0cf"},"references":{"count":2,"sample":[{"doi":"10.1109/weef-","year":2023,"title":"(2024) Unmasking bias in arti ficial intelligence: a systematic review of bias detection and miti- gation strategies in electronic health record-based models","work_id":"00795d58-a299-4c1c-bbe3-5b3c23cd9905","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1186/s13643-023-02243-z","year":2018,"title":"Systems Analysis and Design: An Object-Oriented Ap- proach with UML","work_id":"7ceb7e97-c322-4719-ab65-726ac21351eb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":2,"snapshot_sha256":"ee41de618c4d409cb666fe9cd741057c47ff3ccbe3bf41871f50307a22c87ffc","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"53fd0eea2a26a5afb299aacbc7e866b63a1814d5f5f28c0b293883313d9d49eb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}