{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/devils-in-middle-layers-of-large-vision","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","arxiv_id":"2411.16724","date":"2024-11-23","proceeding":"CVPR 2025 1","authors":["Zhangqi Jiang","Junkai Chen","Beier Zhu","Tingjin Luo","Yankun Shen","Xu Yang"],"abstract":"Hallucinations in Large Vision-Language Models (LVLMs) significantly undermine their reliability, motivating researchers to explore the causes of hallucination. However, most studies primarily focus on the language aspect rather than the visual. In this paper, we address how LVLMs process visual information and whether this process causes hallucination. Firstly, we use the attention lens to identify the stages at which LVLMs handle visual data, discovering that the middle layers are crucial. Moreover, we find that these layers can be further divided into two stages: ''visual information enrichment'' and ''semantic refinement'' which respectively propagate visual data to object tokens and interpret it through text. By analyzing attention patterns during the visual information enrichment stage, we find that real tokens consistently receive higher attention weights than hallucinated ones, serving as a strong indicator of hallucination. Further examination of multi-head attention maps reveals that hallucination tokens often result from heads interacting with inconsistent objects. Based on these insights, we propose a simple inference-time method that adjusts visual attention by integrating information across various heads. Extensive experiments demonstrate that this approach effectively mitigates hallucinations in mainstream LVLMs without additional training costs. Code is available at https://github.com/ZhangqiJiang07/middle_layers_indicating_hallucinations.","url_abs":"https://arxiv.org/abs/2411.16724v3","url_pdf":"https://arxiv.org/pdf/2411.16724v3.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":"devils-in-middle-layers-of-large-vision","repo_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.16724","atlas_url":"https://app.syntology.ai/?focus=2411.16724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16724"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2411.16724"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2411.16724"},"call":"get_harvested_code_for_paper(arxiv_id=\"2411.16724\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2411.16724"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2411.16724\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2411.16724"},"call":"get_concepts_for_paper(arxiv_id=\"2411.16724\")"}],"by_repo":[{"repo":"zhangqijiang07/middle_layers_indicating_hallucinations","kind":"official","samples":10,"ran":8,"instrument":6,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2411.16724.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2411.16724.svg"},"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/zhangqijiang07/middle_layers_indicating_hallucinations","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5,"ran":2,"ran_fixture":1,"unverified":2},"n_samples":10,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":8,"n_ran_checked":2,"n_instrument":6,"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":10,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":4,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"25585704d77cafb4","code_sha256_prefix":"25585704d77cafb4","entry":"combine_coco_captions","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"chair.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/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,"signature":"annotation_path:str/0/str","fixture_out_type":"dict","code_page":"/code/combine-coco-captions","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"code_sha256":"66415dc1dd50f555","code_sha256_prefix":"66415dc1dd50f555","entry":"combine_coco_instances","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"chair.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/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,"signature":"annotation_path:str/0/str","fixture_out_type":"dict","code_page":"/code/combine-coco-instances","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"66415dc1dd50f555"}},{"code_sha256":"592b3c1a88f93d7c","code_sha256_prefix":"592b3c1a88f93d7c","entry":"expand2square","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"eval_data_loader.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/eval_data_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"pil_img:Image/0/?, background_color:tuple/1/int","fixture_out_type":"Image","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/expand2square","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256":"42a46570620cd9fa","code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/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,"signature":"lst:list/1/int, n:int/0/int, k:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"42a46570620cd9fa"},"code_page":"/code/get-chunk","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256":"bb7b96236ae47aaf","code_sha256_prefix":"bb7b96236ae47aaf","entry":"load_generated_captions","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"chair.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/chair.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"cap_file:str/0/str, image_id_key:str/0/str, caption_key:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/load-generated-captions","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"bb7b96236ae47aaf"}},{"code_sha256":"b157d20a4ca304e6","code_sha256_prefix":"b157d20a4ca304e6","entry":"load_llava_model","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"model_manager.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/model_manager.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_path:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"b157d20a4ca304e6"}},{"code_sha256":"a4bcce74aee1b2ac","code_sha256_prefix":"a4bcce74aee1b2ac","entry":"set_act_get_hooks","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, attn_out:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"a4bcce74aee1b2ac"}},{"code_sha256":"076c252c52cbb161","code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/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,"signature":"lst:list/1/int, n:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"076c252c52cbb161"},"code_page":"/code/split-list","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256":"0b24d3aebc841fa4","code_sha256_prefix":"0b24d3aebc841fa4","entry":"get_only_attn_out_contribution","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"0b24d3aebc841fa4"}},{"code_sha256":"62bb863d06274810","code_sha256_prefix":"62bb863d06274810","entry":"llama_new_forward","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","repo_kind":"official","path":"modify_attention.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/modify_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhangqijiang07/middle_layers_indicating_hallucinations when it was checked","mcp_get_code":{"code_sha256":"62bb863d06274810"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f00db0027791f9cd1aebbd31235d0f80ea4d8a1052d0e269559aa162f2e5ad24","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}