{"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/lexicon-level-contrastive-visual-grounding","title":"Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling","arxiv_id":"2403.14551","date":"2024-03-21","proceeding":null,"authors":["Chengxu Zhuang","Evelina Fedorenko","Jacob Andreas"],"abstract":"Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning. Can we make LMs' representations and predictions more accurate (and more human-like) with more ecologically plausible supervision? This paper describes LexiContrastive Grounding (LCG), a grounded language learning procedure that leverages visual supervision to improve textual representations. LexiContrastive Grounding combines a next token prediction strategy with a contrastive visual grounding objective, focusing on early-layer representations that encode lexical information. Across multiple word-learning and sentence-understanding benchmarks, LexiContrastive Grounding not only outperforms standard language-only models in learning efficiency, but also improves upon vision-and-language learning procedures including CLIP, GIT, Flamingo, and Vokenization. Moreover, LexiContrastive Grounding improves perplexity by around 5% on multiple language modeling tasks. This work underscores the potential of incorporating visual grounding into language models, aligning more closely with the multimodal nature of human language acquisition.","url_abs":"https://arxiv.org/abs/2403.14551v1","url_pdf":"https://arxiv.org/pdf/2403.14551v1.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":"lexicon-level-contrastive-visual-grounding","repo_url":"https://github.com/EvLab-MIT/LexiContrastiveGrd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lexicon-level-contrastive-visual-grounding","repo_url":"https://github.com/styfeng/tinydialogues","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"grounded-language-learning","task_name":"Grounded language learning"},{"task_slug":"language-acquisition","task_name":"Language Acquisition"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"vokenization","method_name":"Vokenization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}