{"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/grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","arxiv_id":"2402.18695","date":"2024-02-28","proceeding":null,"authors":["Zilin Xiao","Ming Gong","Paola Cascante-Bonilla","Xingyao Zhang","Jie Wu","Vicente Ordonez"],"abstract":"We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multi-modal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visually-situated reasoning. Our method learns to distinguish similar entities within a vast label space by contrastively training on hard negative pairs in parallel with a sequence-to-sequence objective without an external retriever. During inference, a list of retrieved candidate answers explicitly guides language generation by removing invalid decoding paths. The proposed method achieves significant improvements across different dataset splits in the recently proposed Oven-Wiki benchmark. Accuracy on the Entity seen split rises from 32.7% to 61.5%. It also demonstrates superior performance on the unseen and query splits by a substantial double-digit margin.","url_abs":"https://arxiv.org/abs/2402.18695v2","url_pdf":"https://arxiv.org/pdf/2402.18695v2.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":"grounding-language-models-for-visual-entity","repo_url":"https://github.com/mrzilinxiao/autover","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"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/mrzilinxiao/autover","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MrZilinXiao/AutoVER","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_fixture":2,"ran_draft_wrong":3,"unverified":14},"by_repo_kind":{"official":{"samples":26,"ran":12,"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":"c41616ca93fd79a8","entry":"CLIPVisionTower","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c41616ca93fd79a8"}},{"code_sha256_prefix":"d3336c4c93426ff0","entry":"CausalLMOutputWithPastWithRet","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3336c4c93426ff0"}},{"code_sha256_prefix":"ed5ed903e9e24d08","entry":"accuracy","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed5ed903e9e24d08"}},{"code_sha256_prefix":"0b76a505072cf34e","entry":"contrastive_acc","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b76a505072cf34e"}},{"code_sha256_prefix":"83ada93fd84968cc","entry":"contrastive_loss","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83ada93fd84968cc"}},{"code_sha256_prefix":"418757e4ade61509","entry":"contrastive_loss_with_target","repo":"mrzilinxiao/autover","repo_kind":"official","path":"common_utils/loss_utils.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/common_utils/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"418757e4ade61509"}},{"code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"mrzilinxiao/autover","repo_kind":"official","path":"baselines/submit_gpt4v.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/baselines/submit_gpt4v.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256_prefix":"249898a5ceca22bd","entry":"evaluate_oven","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/official_oven_eval_toolkit.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/official_oven_eval_toolkit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"249898a5ceca22bd"}},{"code_sha256_prefix":"e18691c020115ad3","entry":"load_json","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/bm25_index.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/bm25_index.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e18691c020115ad3"}},{"code_sha256_prefix":"0dc083025b2aad97","entry":"load_jsonl","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/official_oven_eval_toolkit.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/official_oven_eval_toolkit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0dc083025b2aad97"}},{"code_sha256_prefix":"cb38c498b185418c","entry":"prepare_qid2example","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/official_oven_eval_toolkit.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/official_oven_eval_toolkit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb38c498b185418c"}},{"code_sha256_prefix":"0ac33fc045371be4","entry":"run_exactmatch_query","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/exactmatch_query.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/exactmatch_query.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ac33fc045371be4"}},{"code_sha256_prefix":"8db3d394148aae40","entry":"LlavaLlamaForCausalLMWithRet","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8db3d394148aae40"}},{"code_sha256_prefix":"bd94789c33b6b3ce","entry":"LlavaLlamaModelWithRet","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd94789c33b6b3ce"}},{"code_sha256_prefix":"3653c732c4369b00","entry":"LlavaMetaForCausalLMWithRet","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3653c732c4369b00"}},{"code_sha256_prefix":"ee2ab77aead57d40","entry":"LlavaMetaModel","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee2ab77aead57d40"}},{"code_sha256_prefix":"31d0e17da04e4bfe","entry":"RetrieverMetaModel","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31d0e17da04e4bfe"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"mrzilinxiao/autover","repo_kind":"official","path":"common_utils/dist_utils.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/common_utils/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"f1a8171c466e7574","entry":"all_gather_with_grad_torch","repo":"mrzilinxiao/autover","repo_kind":"official","path":"common_utils/dist_utils.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/common_utils/dist_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1a8171c466e7574"}},{"code_sha256_prefix":"e374a58821b3513a","entry":"build_entity_encoder","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e374a58821b3513a"}},{"code_sha256_prefix":"01a59cbdcf1329ec","entry":"build_vision_tower","repo":"MrZilinXiao/AutoVER","repo_kind":"official","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01a59cbdcf1329ec"}},{"code_sha256_prefix":"e8003b1ffefe6856","entry":"find_img_path","repo":"mrzilinxiao/autover","repo_kind":"official","path":"baselines/submit_gpt4v.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/baselines/submit_gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8003b1ffefe6856"}},{"code_sha256_prefix":"fa1225dfac92bc0d","entry":"get_peft_state_maybe_zero_3","repo":"mrzilinxiao/autover","repo_kind":"official","path":"train_oven.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/train_oven.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa1225dfac92bc0d"}},{"code_sha256_prefix":"1c53657305b66e9f","entry":"get_peft_state_non_lora_maybe_zero_3","repo":"mrzilinxiao/autover","repo_kind":"official","path":"train_oven.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/train_oven.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"code_sha256_prefix":"616ffbdc154ed2d8","entry":"maybe_zero_3","repo":"mrzilinxiao/autover","repo_kind":"official","path":"train_oven.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/train_oven.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"616ffbdc154ed2d8"}},{"code_sha256_prefix":"a5be46c82b7c5a66","entry":"run_gpt_query","repo":"mrzilinxiao/autover","repo_kind":"official","path":"bm25_toolkit/bm25_query.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/bm25_toolkit/bm25_query.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5be46c82b7c5a66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}