ExploreToM uses A* search over a domain-specific language to generate adversarial theory-of-mind stories that make LLMs, including GPT-4o, score as low as 0% and 9%, and fine-tuning on the data lifts ToMi accuracy by 27 points.
Mindcraft: Theory of mind modeling for situated dialogue in collaborative tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
ExploreToM uses A* search over a domain-specific language to generate adversarial theory-of-mind stories that make LLMs, including GPT-4o, score as low as 0% and 9%, and fine-tuning on the data lifts ToMi accuracy by 27 points.