Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models
This study adopts a developmental perspective to examine false belief task (FBT) performance in Olmo2 and Pythia language models across training stages. Results show that above-chance FBT performance depends on model size and training volume, emerges late in pretraining, and is most improved by post-training interventions. However, FBT performance is fragile, and situation modeling accuracy generally precedes it. Larger models build partially coherent situation models but display surprising fragility.
[2606.28524] Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models
[Submitted on 26 Jun 2026]
Title:Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models
View a PDF of the paper titled Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models, by Pamela D. Rivi`ere and Cameron Jones and Sean Trott
View PDF HTML (experimental)
Abstract: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 concerns of construct validity remain. We adopt a developmental perspective, tracing the pattern of mental state reasoning behavior -- and likely preconditions for this behavior -- across multiple training stages in the Olmo2 and Pythia language model suites. We find that above-chance FBT performance depends both on model size and sufficient training volume, emerges relatively late in pretraining, and is most improved by post-training interventions (SFT, DPO) in the condition most diagnostic of mentalizing (False Belief, Implicit). However, FBT performance is fragile: consistent with past work, the use of non-factive verbs (e.g., thinks) increases false belief attributions even in the True Belief condition. To contextualize these findings, we track the emergence of situation modeling: the ability to report on basic factual properties of a described scene. Situation modeling accuracy generally precedes and exceeds FBT accuracy, yet situational representations also prove surprisingly incoherent in certain respects: when asked about the knowledge states of the Antagonist agent -- who always knows the item's true location -- Olmo2 13b is consistently influenced both by the Target agent's knowledge state and the presence of non-factive verbs. Together, these results suggest that larger, sufficiently trained models build partially coherent situation models in a developmentally appropriate sequence, yet display surprising fragility -- highlighting the value of developmental and stress-testing approaches for evaluating LLM capabilities.
Comments: Non-archival submission to the First Workshop on Computational Developmental Linguistics
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2606.28524 [cs.CL]
(or arXiv:2606.28524v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.28524
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Pamela Riviere [view email] [v1] Fri, 26 Jun 2026 18:21:16 UTC (2,351 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models, by Pamela D. Rivi`ere and Cameron Jones and Sean Trott
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)