Aligning Large Language Models through Synthetic Feedback

Sungdong Kim, Sanghwan Bae, Jamin Shin, Soyoung Kang, Donghyun Kwak, Kang Yoo, Minjoon Seo


Abstract
Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs such as ChatGPT. In this work, we propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations and proprietary LLMs. First, we perform reward modeling (RM) with synthetic feedback by contrasting responses from vanilla LLMs with various sizes and prompts. Then, we use the RM to simulate high-quality demonstrations to train a supervised policy and further optimize the model with reinforcement learning. Our resulting model, Aligned Language Model with Synthetic Training dataset (ALMoST), outperforms recent open-sourced models, which are trained on the outputs of InstructGPT or human-annotated demonstrations, in alignment benchmarks. In human evaluation, our model is preferred to Alpaca and Dolly-v2, 55.0% and 58.5% of the time, respectively. Further analyses demonstrate the efficacy and importance of synthetic feedback in our framework.
Anthology ID:
2023.emnlp-main.844
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:
13677–13700
Language:
URL:
https://aclanthology.org/2023.emnlp-main.844
DOI:
10.18653/v1/2023.emnlp-main.844
Bibkey:
Cite (ACL):
Sungdong Kim, Sanghwan Bae, Jamin Shin, Soyoung Kang, Donghyun Kwak, Kang Yoo, and Minjoon Seo. 2023. Aligning Large Language Models through Synthetic Feedback. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13677–13700, Singapore. Association for Computational Linguistics.
Cite (Informal):
Aligning Large Language Models through Synthetic Feedback (Kim et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.844.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.844.mp4