1 code implementation • 8 Mar 2024 • Lennart Wachowiak, Andrew Coles, Oya Celiktutan, Gerard Canal
We find that GPT-4 strongly outperforms other models, generating answers that correlate strongly with users' answers in two studies $\unicode{x2014}$ the first study dealing with selecting the most appropriate communicative act for a robot in various situations ($r_s$ = 0. 82), and the second with judging the desirability, intentionality, and surprisingness of behavior ($r_s$ = 0. 83).
2 code implementations • Proceedings of the AAAI Conference on Artificial Intelligence, 36(9) 2022 • Gerard Canal, Senka Krivic ́, Paul Luff, Andrew Coles
Our method can generate natural language descriptions of plans including causal explanations.