4 papers
Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust
Amogh Mannekote, Adam Davies, Guohao Li +4
As LLMs are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigned ro…
Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments
Amogh Mannekote, Adam Davies, Jina Kang +1
Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of…
Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests
Amogh Mannekote, Jinseok Nam, Ziming Li +3
Indirect User Requests (IURs), such as "It's cold in here" instead of "Could you please increase the temperature?" are common in human-human task-oriented dialogue and require worl…
Towards Compositionally Generalizable Semantic Parsing in Large Language Models: A Survey
Amogh Mannekote
Compositional generalization is the ability of a model to generalize to complex, previously unseen types of combinations of entities from just having seen the primitives. This type…