activity
20242026
collaborators

7 papers

cs.CL2026

Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models

Pamela D. Rivière, Cameron Jones, Sean Trott

Recent work suggests that Large Language Models (LLMs) are sensitive to the belief states of agents described by text, as measured by the false belief task (FBT), yet persistent co…

cs.CL2026

How Open Must Language Models be to Enable Reliable Scientific Inference?

James A. Michaelov, Catherine Arnett, Tyler A. Chang +7

How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this paper, we analyze how restrictions…

cs.CL2026

Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs

Sean Trott, Samuel Taylor, Cameron Jones +2

Research on mental state reasoning in language models (LMs) has the potential to inform theories of human social cognition--such as the theory that mental state reasoning emerges i…

cs.CL2026

Capacity Constraints and the Multilingual Penalty for Lexical Disambiguation

Sean Trott, Pamela D. Rivière

Multilingual language models (LMs) sometimes under-perform their monolingual counterparts, possibly due to capacity limitations. We quantify this ``multilingual penalty'' for lexic…

cs.CL2025

Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity

Pamela D. Rivière, Sean Trott

Despite an in-principle understanding of self-attention matrix operations in Transformer language models (LMs), it remains unclear precisely how these operations map onto interpret…

cs.CL2025

Evaluating Contextualized Representations of (Spanish) Ambiguous Words: A New Lexical Resource and Empirical Analysis

Pamela D. Rivière, Anne L. Beatty-Martínez, Sean Trott

Lexical ambiguity -- where a single wordform takes on distinct, context-dependent meanings -- serves as a useful tool to compare across different language models' (LMs') ability to…