{"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/2408-01419","title":"DebateQA: Evaluating Question Answering on Debatable Knowledge","arxiv_id":"2408.01419","date":"2024-08-02","proceeding":null,"authors":["Rongwu Xu","Xuan Qi","Zehan Qi","Wei Xu","Zhijiang Guo"],"abstract":"The rise of large language models (LLMs) has enabled us to seek answers to inherently debatable questions on LLM chatbots, necessitating a reliable way to evaluate their ability. However, traditional QA benchmarks assume fixed answers are inadequate for this purpose. To address this, we introduce DebateQA, a dataset of 2,941 debatable questions, each accompanied by multiple human-annotated partial answers that capture a variety of perspectives. We develop two metrics: Perspective Diversity, which evaluates the comprehensiveness of perspectives, and Dispute Awareness, which assesses if the LLM acknowledges the question's debatable nature. Experiments demonstrate that both metrics align with human preferences and are stable across different underlying models. Using DebateQA with two metrics, we assess 12 popular LLMs and retrieval-augmented generation methods. Our findings reveal that while LLMs generally excel at recognizing debatable issues, their ability to provide comprehensive answers encompassing diverse perspectives varies considerably.","url_abs":"https://arxiv.org/abs/2408.01419v1","url_pdf":"https://arxiv.org/pdf/2408.01419v1.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":"2408-01419","repo_url":"https://github.com/pillowsofwind/debateqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.01419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01419"}},"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/pillowsofwind/debateqa","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"3dbc1ddbfd264f0e","entry":"calculate_conditional_perplexity_batch","repo":"pillowsofwind/debateqa","repo_kind":"official","path":"scripts/eval_PD.py","file_url":"https://github.com/pillowsofwind/debateqa/blob/HEAD/scripts/eval_PD.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3dbc1ddbfd264f0e"}},{"code_sha256_prefix":"e76ca8cb0b0240ce","entry":"get_model_path","repo":"pillowsofwind/debateqa","repo_kind":"official","path":"scripts/eval_DA.py","file_url":"https://github.com/pillowsofwind/debateqa/blob/HEAD/scripts/eval_DA.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e76ca8cb0b0240ce"}},{"code_sha256_prefix":"431161166ebfe71a","entry":"get_model_path","repo":"pillowsofwind/debateqa","repo_kind":"official","path":"scripts/eval_PD.py","file_url":"https://github.com/pillowsofwind/debateqa/blob/HEAD/scripts/eval_PD.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":"431161166ebfe71a"}},{"code_sha256_prefix":"1d13608372e35054","entry":"is_debatable_answer","repo":"pillowsofwind/debateqa","repo_kind":"official","path":"scripts/eval_DA.py","file_url":"https://github.com/pillowsofwind/debateqa/blob/HEAD/scripts/eval_DA.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d13608372e35054"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}