{"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/reducing-hallucinations-in-vision-language","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","arxiv_id":"2410.15778","date":"2024-10-21","proceeding":null,"authors":["Sheng Liu","Haotian Ye","Lei Xing","James Zou"],"abstract":"Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs. This paper investigates the underlying mechanisms of hallucination, focusing on the unique structure of LVLMs that distinguishes them from large language models (LLMs). We identify that hallucinations often arise from the sensitivity of text decoders to vision inputs, a natural phenomenon when image encoders and text decoders are pre-trained separately. Inspired by this, we introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features. As a task-agnostic test-time intervention, VTI can be easily applied to any problem without additional cost. Extensive experiments demonstrate that it can effectively reduce hallucinations and outperform baseline methods across multiple metrics, highlighting the critical role of vision feature stability in LVLMs.","url_abs":"https://arxiv.org/abs/2410.15778v2","url_pdf":"https://arxiv.org/pdf/2410.15778v2.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":"reducing-hallucinations-in-vision-language","repo_url":"https://github.com/shengliu66/vti","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.15778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15778"}},"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/shengliu66/vti","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"bab95a1590abaf99","entry":"get_prompts","repo":"shengliu66/vti","repo_kind":"official","path":"vti_utils/icv_utils.py","file_url":"https://github.com/shengliu66/vti/blob/HEAD/vti_utils/icv_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bab95a1590abaf99"}},{"code_sha256_prefix":"872eda81845feaa5","entry":"mask_patches","repo":"shengliu66/vti","repo_kind":"official","path":"vti_utils/icv_utils.py","file_url":"https://github.com/shengliu66/vti/blob/HEAD/vti_utils/icv_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"872eda81845feaa5"}},{"code_sha256_prefix":"c9105024c097d7ad","entry":"process_image","repo":"shengliu66/vti","repo_kind":"official","path":"vti_utils/icv_utils.py","file_url":"https://github.com/shengliu66/vti/blob/HEAD/vti_utils/icv_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9105024c097d7ad"}},{"code_sha256_prefix":"76cb05a76ebdeb15","entry":"load_image","repo":"shengliu66/vti","repo_kind":"official","path":"experiments/eval/run_mmhal_vti.py","file_url":"https://github.com/shengliu66/vti/blob/HEAD/experiments/eval/run_mmhal_vti.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76cb05a76ebdeb15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}