Papers › Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling

21 Mar 2024arXiv:2403.14551archive 2025-07-28

Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas

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.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

EvLab-MIT/LexiContrastiveGrd mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Visual Grounding Helps Learn Word Meanings in Low-Data Regimes (arXiv:2310.13257; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
styfeng/tinydialogues mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Is Child-Directed Speech Effective Training Data for Language Models? (arXiv:2408.03617; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Grounded language learningLanguage AcquisitionLanguage ModelingLanguage ModellingSentenceVisual Grounding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPVokenization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections