{"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/debunc-mitigating-hallucinations-in-large","title":"DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics","arxiv_id":"2407.06426","date":"2024-07-08","proceeding":null,"authors":["Luke Yoffe","Alfonso Amayuelas","William Yang Wang"],"abstract":"Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs) by having multiple agents discuss solutions to a problem over several rounds of debate. However, models often generate incorrect yet confident-sounding responses, which can mislead others. This issue arises partly because agents do not consider how confident their peers are. To address this, we propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence. Confidence is then conveyed through a modified attention mechanism that adjusts token weights, or through textual prompts. Evaluations across benchmarks show that attention-based methods are particularly effective and that performance continues to improve as uncertainty estimation becomes more reliable. The code is available at https://github.com/lukeyoffe/debunc.","url_abs":"https://arxiv.org/abs/2407.06426v2","url_pdf":"https://arxiv.org/pdf/2407.06426v2.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":"debunc-mitigating-hallucinations-in-large","repo_url":"https://github.com/lukeyoffe/debunc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.06426","atlas_url":"https://app.syntology.ai/?focus=2407.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06426"}},"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/lukeyoffe/debunc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":2,"ran":4},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/models/modeling_llama.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/models/modeling_mistral.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/models/modeling_mistral.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d61c483a3c2b3156"}},{"code_sha256_prefix":"bac65c3dafaec040","entry":"apply_rotary_pos_emb","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/models/modeling_llama.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bac65c3dafaec040"}},{"code_sha256_prefix":"298f0988fadc57a7","entry":"get_uncertainties","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/debate/eval_utils.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/debate/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"298f0988fadc57a7"}},{"code_sha256_prefix":"936b0596659cb58f","entry":"mean_and_95ci","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/debate/eval_utils.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/debate/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"936b0596659cb58f"}},{"code_sha256_prefix":"674c6c7d171e8309","entry":"most_frequent","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/debate/eval_utils.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/debate/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"674c6c7d171e8309"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/models/modeling_llama.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"00525981ac67214b","entry":"unc_to_confidence","repo":"lukeyoffe/debunc","repo_kind":"official","path":"src/debate/gen_utils.py","file_url":"https://github.com/lukeyoffe/debunc/blob/HEAD/src/debate/gen_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00525981ac67214b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}