{"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/aligning-large-multi-modal-model-with-robust","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","arxiv_id":"2306.14565","date":"2023-06-26","proceeding":null,"authors":["Fuxiao Liu","Kevin Lin","Linjie Li","JianFeng Wang","Yaser Yacoob","Lijuan Wang"],"abstract":"Despite the promising progress in multi-modal tasks, current large multi-modal models (LMMs) are prone to hallucinating inconsistent descriptions with respect to the associated image and human instructions. This paper addresses this issue by introducing the first large and diverse visual instruction tuning dataset, named Large-scale Robust Visual (LRV)-Instruction. Our dataset comprises 400k visual instructions generated by GPT4, covering 16 vision-and-language tasks with open-ended instructions and answers. Unlike existing studies that primarily focus on positive instruction samples, we design LRV-Instruction to include both positive and negative instructions for more robust visual instruction tuning. Our negative instructions are designed at three semantic levels: (i) Nonexistent Object Manipulation, (ii) Existent Object Manipulation and (iii) Knowledge Manipulation. To efficiently measure the hallucination generated by LMMs, we propose GPT4-Assisted Visual Instruction Evaluation (GAVIE), a stable approach to evaluate visual instruction tuning like human experts. GAVIE does not require human-annotated groundtruth answers and can adapt to diverse instruction formats. We conduct comprehensive experiments to investigate the hallucination of LMMs. Our results demonstrate existing LMMs exhibit significant hallucinations when presented with our negative instructions, particularly Existent Object and Knowledge Manipulation instructions. Moreover, we successfully mitigate hallucination by finetuning MiniGPT4 and mPLUG-Owl on LRV-Instruction while improving performance on several public datasets compared to state-of-the-art methods. Additionally, we observed that a balanced ratio of positive and negative instances in the training data leads to a more robust model. Code and data are available at https://github.com/FuxiaoLiu/LRV-Instruction.","url_abs":"https://arxiv.org/abs/2306.14565v4","url_pdf":"https://arxiv.org/pdf/2306.14565v4.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":"aligning-large-multi-modal-model-with-robust","repo_url":"https://github.com/FuxiaoLiu/LRV-Instruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"aligning-large-multi-modal-model-with-robust","repo_url":"https://github.com/FuxiaoLiu/VisualNews-Repository","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"aligning-large-multi-modal-model-with-robust","repo_url":"https://github.com/fuxiaoliu/mmc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"aligning-large-multi-modal-model-with-robust","repo_url":"https://github.com/h-zhao1997/cobra","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LRV-Instruction-7B","rank_in_archive_order":190,"of":231,"metrics":{"GPT-4 score":"31.7±0.1","Params":"7B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-3","task":"Visual Question Answering (VQA)","dataset":"HallusionBench","model":"LRV-Instruct","rank_in_archive_order":3,"of":4,"metrics":{"Question Pair Acc\t":"1.57"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.14565","atlas_url":"https://app.syntology.ai/?focus=2306.14565","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2306.14565"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2306.14565\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2306.14565"},"call":"get_concepts_for_paper(arxiv_id=\"2306.14565\")"}],"by_repo":[{"repo":"FuxiaoLiu/LRV-Instruction","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.10774"],"harvested_for_calls":[{"arxiv_id":"2311.10774","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.10774"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.10774\")"}]},{"repo":"FuxiaoLiu/VisualNews-Repository","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.10774"],"harvested_for_calls":[{"arxiv_id":"2311.10774","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.10774"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.10774\")"}]},{"repo":"fuxiaoliu/mmc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.10774"],"harvested_for_calls":[{"arxiv_id":"2311.10774","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.10774"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.10774\")"}]},{"repo":"h-zhao1997/cobra","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.14520"],"harvested_for_calls":[{"arxiv_id":"2403.14520","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.14520"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.14520\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3039b7f43d7c1b2566f928f54c40943fdd3266c20110f67f652fbcb9743e1322","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}