{"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/convis-contrastive-decoding-with","title":"ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models","arxiv_id":"2408.13906","date":"2024-08-25","proceeding":null,"authors":["Yeji Park","Deokyeong Lee","Junsuk Choe","Buru Chang"],"abstract":"Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a novel training-free contrastive decoding method. ConVis leverages a text-to-image (T2I) generation model to semantically reconstruct the given image from hallucinated captions. By comparing the contrasting probability distributions produced by the original and reconstructed images, ConVis enables MLLMs to capture visual contrastive signals that penalize hallucination generation. Notably, this method operates purely within the decoding process, eliminating the need for additional data or model updates. Our extensive experiments on five popular benchmarks demonstrate that ConVis effectively reduces hallucinations across various MLLMs, highlighting its potential to enhance model reliability.","url_abs":"https://arxiv.org/abs/2408.13906v1","url_pdf":"https://arxiv.org/pdf/2408.13906v1.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":"convis-contrastive-decoding-with","repo_url":"https://github.com/yejipark-m/convis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.13906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13906"}},"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/yejipark-m/convis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"4cb732f513d69dfd","entry":"disabled_train","repo":"yejipark-m/convis","repo_kind":"official","path":"minigpt4/models/blip2.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/minigpt4/models/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"13cb3dd1e9e1ed71","entry":"get_eval","repo":"yejipark-m/convis","repo_kind":"official","path":"eval/eval_gpt_review_bench.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/eval/eval_gpt_review_bench.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":"13cb3dd1e9e1ed71"}},{"code_sha256_prefix":"9c2bf5dd6d37b5f0","entry":"get_image_file_location","repo":"yejipark-m/convis","repo_kind":"official","path":"eval/utils.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/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":"9c2bf5dd6d37b5f0"}},{"code_sha256_prefix":"763f6fe20bd52fbb","entry":"parse_score","repo":"yejipark-m/convis","repo_kind":"official","path":"eval/eval_gpt_review_bench.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/eval/eval_gpt_review_bench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"763f6fe20bd52fbb"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"yejipark-m/convis","repo_kind":"official","path":"minigpt4/models/base_model.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/minigpt4/models/base_model.py","link_basis":"harvester_set","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":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"yejipark-m/convis","repo_kind":"official","path":"minigpt4/models/base_model.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/minigpt4/models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"5589790082e0bad0","entry":"check_same_by_chatgpt","repo":"yejipark-m/convis","repo_kind":"official","path":"eval/utils.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5589790082e0bad0"}},{"code_sha256_prefix":"4747cf44453074cf","entry":"evaluate_by_chatgpt","repo":"yejipark-m/convis","repo_kind":"official","path":"eval/utils.py","file_url":"https://github.com/yejipark-m/convis/blob/HEAD/eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4747cf44453074cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}