565 citations · 675 across the 33 of their papers we have counts for
10 papers · 1 filter
Emergence of Linear Truth Encodings in Language Models
Shauli Ravfogel, Gilad Yehudai, Tal Linzen +2
Recent probing studies reveal that large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear. We…
To model human linguistic prediction, make LLMs less superhuman
Byung-Doh Oh, Tal Linzen
When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make pred…
Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
Carter Blum, Katja Filippova, Ann Yuan +8
Large language models (LLMs) struggle with cross-lingual knowledge transfer: they sometimes hallucinate when asked in one language about facts expressed in a different language dur…
RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context
Jackson Petty, Michael Y. Hu, Wentao Wang +3
Large language models (LLMs) are increasingly used to solve complex tasks where they must retrieve and compose many pieces of in-context information in long reasoning chains. For m…
Multilingual Prompting for Improving LLM Generation Diversity
Qihan Wang, Shidong Pan, Tal Linzen +1
Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitig…
Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Alex Warstadt, Aaron Mueller, Leshem Choshen +8
Children can acquire language from less than 100 million words of input. Large language models are far less data-efficient: they typically require 3 or 4 orders of magnitude more d…
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
Linlu Qiu, Fei Sha, Kelsey Allen +3
Large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs must construct representations of the world an…
BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop
Lucas Charpentier, Leshem Choshen, Ryan Cotterell +11
BabyLM aims to dissolve the boundaries between cognitive modeling and language modeling. We call for both workshop papers and for researchers to join the 3rd BabyLM competition. As…
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
Michael Y. Hu, Jackson Petty, Chuan Shi +2
Pretraining language models on formal language can improve their acquisition of natural language. Which features of the formal language impart an inductive bias that leads to effec…
Rapid Word Learning Through Meta In-Context Learning
Wentao Wang, Guangyuan Jiang, Tal Linzen +1
Humans can quickly learn a new word from a few illustrative examples, and then systematically and flexibly use it in novel contexts. Yet the abilities of current language models fo…