{"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/visualgptscore-visio-linguistic-reasoning","title":"Revisiting the Role of Language Priors in Vision-Language Models","arxiv_id":"2306.01879","date":"2023-06-02","proceeding":null,"authors":["Zhiqiu Lin","Xinyue Chen","Deepak Pathak","Pengchuan Zhang","Deva Ramanan"],"abstract":"Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\\textit{generative VLMs}$ that are trained for next-word generation given an image. We explore their zero-shot performance on the illustrative task of image-text retrieval across 8 popular vision-language benchmarks. Our first observation is that they can be repurposed for discriminative tasks (such as image-text retrieval) by simply computing the match score of generating a particular text string given an image. We call this probabilistic score the $\\textit{Visual Generative Pre-Training Score}$ (VisualGPTScore). While the VisualGPTScore produces near-perfect accuracy on some retrieval benchmarks, it yields poor accuracy on others. We analyze this behavior through a probabilistic lens, pointing out that some benchmarks inadvertently capture unnatural language distributions by creating adversarial but unlikely text captions. In fact, we demonstrate that even a \"blind\" language model that ignores any image evidence can sometimes outperform all prior art, reminiscent of similar challenges faced by the visual-question answering (VQA) community many years ago. We derive a probabilistic post-processing scheme that controls for the amount of linguistic bias in generative VLMs at test time without having to retrain or fine-tune the model. We show that the VisualGPTScore, when appropriately debiased, is a strong zero-shot baseline for vision-language understanding, oftentimes producing state-of-the-art accuracy.","url_abs":"https://arxiv.org/abs/2306.01879v4","url_pdf":"https://arxiv.org/pdf/2306.01879v4.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":"visualgptscore-visio-linguistic-reasoning","repo_url":"https://github.com/linzhiqiu/visual_gpt_score","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset":"Winoground","model":"BLIP (VisualGPTScore, α-tuned)","rank_in_archive_order":46,"of":114,"metrics":{"Group Score":"16.8","Image Score":"21.5","Text Score":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset":"Winoground","model":"BLIP (ITM)","rank_in_archive_order":50,"of":114,"metrics":{"Group Score":"13.3","Image Score":"15.8","Text Score":"35.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset":"Winoground","model":"BLIP (ITC)","rank_in_archive_order":80,"of":114,"metrics":{"Group Score":"6.5","Image Score":"9.0","Text Score":"28.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.01879","atlas_url":"https://app.syntology.ai/?focus=2306.01879","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":"2306.01879"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2306.01879\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2306.01879"},"call":"get_concepts_for_paper(arxiv_id=\"2306.01879\")"}],"by_repo":[{"repo":"linzhiqiu/visual_gpt_score","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"9ced17cf3b5938d285f1d33d12f6afe12a4fce8a7c8cd4e4d13c51049033077f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}