← Search

Amogh Mannekote

2 accepted papers

2025

Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments

AAAI 2025technical

Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human behavior, such approaches have not gone beyond rudimentary proof…

2025

Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests

COLING 2025main

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 world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effe…

Cited by 1SourcePDFScholar