{"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/mitigating-hallucinations-in-large-vision-4","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","arxiv_id":"2502.20750","date":"2025-02-28","proceeding":null,"authors":["Jiaqi Bai","Hongcheng Guo","Zhongyuan Peng","Jian Yang","Zhoujun Li","Mohan Li","Zhihong Tian"],"abstract":"Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do not exist in the image. In this paper, we reveal that object hallucination can be attributed to overconfidence in irrelevant visual features when soft visual tokens map to the LLM's word embedding space. Specifically, by figuring out the semantic similarity between visual tokens and LLM's word embedding, we observe that the smoothness of similarity distribution strongly correlates with the emergence of object hallucinations. To mitigate hallucinations, we propose using the Variational Information Bottleneck (VIB) to alleviate overconfidence by introducing stochastic noise, facilitating the constraining of irrelevant information. Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution. We adapt the proposed AdaVIB across distinct model architectures. Experimental results demonstrate that the proposed AdaVIB mitigates object hallucinations by effectively alleviating the overconfidence in irrelevant visual features, with consistent improvements on two object hallucination benchmarks.","url_abs":"https://arxiv.org/abs/2502.20750v1","url_pdf":"https://arxiv.org/pdf/2502.20750v1.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":"mitigating-hallucinations-in-large-vision-4","repo_url":"https://github.com/jiaqi5598/adavib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-hallucination","task_name":"Object Hallucination"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.20750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20750"}},"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/jiaqi5598/adavib","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_violates":1,"unverified":8},"by_repo_kind":{"official":{"samples":11,"ran":3,"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":"a3826392847cbef3","entry":"count_trainable_parameters","repo":"jiaqi5598/adavib","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/utils.py","link_basis":"harvester_set","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":"a3826392847cbef3"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"jiaqi5598/adavib","repo_kind":"official","path":"minigpt4/models/blip2.py","file_url":"https://github.com/jiaqi5598/adavib/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":"cb33571427334815","entry":"tile","repo":"jiaqi5598/adavib","repo_kind":"official","path":"minigpt4/models/base_model.py","file_url":"https://github.com/jiaqi5598/adavib/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":"jiaqi5598/adavib","repo_kind":"official","path":"minigpt4/models/base_model.py","file_url":"https://github.com/jiaqi5598/adavib/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":"64cd9e71a82a2a94","entry":"create_eva_vit_g","repo":"jiaqi5598/adavib","repo_kind":"official","path":"minigpt4/models/eva_vit.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/minigpt4/models/eva_vit.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":"64cd9e71a82a2a94"}},{"code_sha256_prefix":"5f2ab8de0b6931ca","entry":"generic_train","repo":"jiaqi5598/adavib","repo_kind":"official","path":"coco_eval.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/coco_eval.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":"5f2ab8de0b6931ca"}},{"code_sha256_prefix":"87dda5e48a6f979b","entry":"get_checkpoint_callback","repo":"jiaqi5598/adavib","repo_kind":"official","path":"callback.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/callback.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":"87dda5e48a6f979b"}},{"code_sha256_prefix":"da7106d308e830d0","entry":"get_early_stopping_callback","repo":"jiaqi5598/adavib","repo_kind":"official","path":"callback.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/callback.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":"da7106d308e830d0"}},{"code_sha256_prefix":"5b438ab40d436d5c","entry":"kofn","repo":"jiaqi5598/adavib","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/utils.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":"5b438ab40d436d5c"}},{"code_sha256_prefix":"84b847bd3c5f6032","entry":"pickle_load","repo":"jiaqi5598/adavib","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/utils.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":"84b847bd3c5f6032"}},{"code_sha256_prefix":"ba97e5823244ca98","entry":"sortish_sampler_indices","repo":"jiaqi5598/adavib","repo_kind":"official","path":"sampler.py","file_url":"https://github.com/jiaqi5598/adavib/blob/HEAD/sampler.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":"ba97e5823244ca98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}