The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values

Hannah Kirk, Andrew Bean, Bertie Vidgen, Paul Rottger, Scott Hale


Abstract
Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective human preferences and values. In this paper, we survey existing approaches for learning from human feedback, drawing on 95 papers primarily from the ACL and arXiv repositories. First, we summarise the past, pre-LLM trends for integrating human feedback into language models. Second, we give an overview of present techniques and practices, as well as the motivations for using feedback; conceptual frameworks for defining values and preferences; and how feedback is collected and from whom. Finally, we encourage a better future of feedback learning in LLMs by raising five unresolved conceptual and practical challenges.
Anthology ID:
2023.emnlp-main.148
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2409–2430
Language:
URL:
https://aclanthology.org/2023.emnlp-main.148
DOI:
10.18653/v1/2023.emnlp-main.148
Bibkey:
Cite (ACL):
Hannah Kirk, Andrew Bean, Bertie Vidgen, Paul Rottger, and Scott Hale. 2023. The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2409–2430, Singapore. Association for Computational Linguistics.
Cite (Informal):
The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values (Kirk et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.148.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.148.mp4