Signals 4 · free daily AI digest

Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model

Paper recorded by Signals 4 on 2026-09-10 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.CL · 自然语言处理 · first seen 2026-09-11

Abstract

A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language model (DeBERTa) trained on 10M words: before training, visually grounded tokens receive embeddings derived from the image regions they label; other tokens start r

Read on arXiv →

#68 most recent of 186 cs.CL papers we have recorded · ↑ newer: Nuha-Speech: Building General-Purpose Arabic Speech-LLMs · ↓ older: Epistemic orientation predicts legislative effectiveness among members
Cite this page: Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model: the #68 most recent of 186 cs.CL papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/augustinian-babylm-what-ostensive-definition-can-and-cannot-teach-a-small-langua.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions