{"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/on-the-risk-of-misinformation-pollution-with","title":"On the Risk of Misinformation Pollution with Large Language Models","arxiv_id":"2305.13661","date":"2023-05-23","proceeding":null,"authors":["Yikang Pan","Liangming Pan","Wenhu Chen","Preslav Nakov","Min-Yen Kan","William Yang Wang"],"abstract":"In this paper, we comprehensively investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems. We establish a threat model and simulate potential misuse scenarios, both unintentional and intentional, to assess the extent to which LLMs can be utilized to produce misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation in the performance of ODQA systems. To mitigate the harm caused by LLM-generated misinformation, we explore three defense strategies: prompting, misinformation detection, and majority voting. While initial results show promising trends for these defensive strategies, much more work needs to be done to address the challenge of misinformation pollution. Our work highlights the need for further research and interdisciplinary collaboration to address LLM-generated misinformation and to promote responsible use of LLMs.","url_abs":"https://arxiv.org/abs/2305.13661v2","url_pdf":"https://arxiv.org/pdf/2305.13661v2.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":"on-the-risk-of-misinformation-pollution-with","repo_url":"https://github.com/MexicanLemonade/LLM-Misinfo-QA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"misinformation","task_name":"Misinformation"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.13661","atlas_url":"https://app.syntology.ai/?focus=2305.13661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13661"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/MexicanLemonade/LLM-Misinfo-QA","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":1,"samples":[{"code_sha256_prefix":"b3157ef7886de898","entry":"load_dpr","repo":"MexicanLemonade/LLM-Misinfo-QA","repo_kind":"official","path":"src/pipeline.py","file_url":"https://github.com/MexicanLemonade/LLM-Misinfo-QA/blob/HEAD/src/pipeline.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3157ef7886de898"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}