AI Paper Atlas

Research map / Large language models / Agents, code and math

MovieGraph-ToM: Evaluating Long-Range Theory of Mind in Large Language Models via Implicit Social-Causal Graphs

Tingjiang Wei, Qin Ni, Rong Gao, Yingying Wang, Liang He

AAAI 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
switch from single-choice to multiple-choice questionsgpt-4o-mini · MovieGraph-ToMaccuracy: 93.8 -> 35.4Hurt
switch from single-choice to multiple-choice questionsllava-onevision-qwen2-7b · MovieGraph-ToMaccuracy: 84.6 -> 26.9Hurt
switch from single-choice to multiple-choice questionsgemini-2.5-pro · MovieGraph-ToMaccuracy: 96.4 -> 70.8Hurt
switch from multiple-choice to open-ended generationgpt-4.1 and gemini-2.5-pro · MovieGraph-ToMopen-ended score: 0.675 and 0.674 (below 0.7 threshold)Hurt
increase reasoning depth from 1 to 3gemini-2.5-pro · MovieGraph-ToMexplanation score: 0.892 -> 0.760Hurt
increase reasoning depth to 3most models · MovieGraph-ToMaccuracyNo clear effect
use larger / stronger modelgemini-2.5-pro vs smaller models · MovieGraph-ToMoverall accuracy: 75.1 -> 92.0Improved
add counterfactual premise to unexplored branchesall evaluated models · MovieGraph-ToMCounterfactual Recovery ScoreImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy