Imperial College London

ProfessorMurrayShanahan

Faculty of EngineeringDepartment of Computing

Professor in Cognitive Robotics
 
 
 
//

Contact

 

+44 (0)20 7594 8262m.shanahan Website

 
 
//

Location

 

407BHuxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Shanahan:2023:10.1038/s41586-023-06647-8,
author = {Shanahan, M and McDonell, K and Reynolds, L},
doi = {10.1038/s41586-023-06647-8},
journal = {Nature},
pages = {493--498},
title = {Role-play with large language models},
url = {http://dx.doi.org/10.1038/s41586-023-06647-8},
volume = {623},
year = {2023}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - As dialogue agents become increasingly human-like in their performance, we must develop effective ways to describe their behaviour in high-level terms without falling into the trap of anthropomorphism. In this paper, we foreground the concept of role-play. Casting dialogue agent behaviour in terms of role-play allows us to draw on familiar folk psychological terms, without ascribing human characteristics to language models they in fact lack. Two important cases of dialogue agent behaviour are addressed this way, namely (apparent) deception and (apparent) self-awareness.
AU - Shanahan,M
AU - McDonell,K
AU - Reynolds,L
DO - 10.1038/s41586-023-06647-8
EP - 498
PY - 2023///
SN - 0028-0836
SP - 493
TI - Role-play with large language models
T2 - Nature
UR - http://dx.doi.org/10.1038/s41586-023-06647-8
UR - https://www.nature.com/articles/s41586-023-06647-8
UR - http://hdl.handle.net/10044/1/106938
VL - 623
ER -