{"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/less-is-more-mitigating-multimodal","title":"Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective","arxiv_id":"2402.14545","date":"2024-02-22","proceeding":null,"authors":["Zihao Yue","Liang Zhang","Qin Jin"],"abstract":"Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders the model's ability to timely terminate generation, leading to continued outputs beyond visual perception limits. By investigating how the model decides to terminate generation with EOS, the special end-of-sentence token, we find that the model assesses the completeness of the entire sequence by comparing the generated text with the image. This observation suggests that the model possesses an inherent potential of making proper EOS decisions based on its visual perception to avoid overly lengthy outputs. To take advantage of such potential, we explore two methods to mitigate multimodal hallucinations: a training objective that enables the model to reduce hallucinations by learning from regular instruction data, and a data filtering strategy to prevent harmful training data from exacerbating model hallucinations. Both methods significantly improve the hallucination performance of LMMs, without requiring any additional data or knowledge.","url_abs":"https://arxiv.org/abs/2402.14545v2","url_pdf":"https://arxiv.org/pdf/2402.14545v2.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":"less-is-more-mitigating-multimodal","repo_url":"https://github.com/yuezih/less-is-more","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.14545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14545"}},"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/yuezih/less-is-more","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":6,"ran":2,"ran_violates":1,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":"20e4f665698a3d18","entry":"collate_fn","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa_loader.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e4f665698a3d18"}},{"code_sha256_prefix":"25585704d77cafb4","entry":"combine_coco_captions","repo":"yuezih/less-is-more","repo_kind":"official","path":"CHAIR-eval/chair.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/CHAIR-eval/chair.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"code_sha256_prefix":"66415dc1dd50f555","entry":"combine_coco_instances","repo":"yuezih/less-is-more","repo_kind":"official","path":"CHAIR-eval/chair.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/CHAIR-eval/chair.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"66415dc1dd50f555"}},{"code_sha256_prefix":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/mm_utils.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e03b180fa317c9a"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa_mmbench.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/eval/model_vqa_mmbench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256_prefix":"897c16b1c81103f4","entry":"load_generated_captions","repo":"yuezih/less-is-more","repo_kind":"official","path":"CHAIR-eval/chair.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/CHAIR-eval/chair.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"897c16b1c81103f4"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/predict.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/predict.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"468eedeba67f1b00","entry":"resize_and_pad_image","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/mm_utils.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"468eedeba67f1b00"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/mm_utils.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"yuezih/less-is-more","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}