Baolin Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Baolin Peng has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jianfeng Gao
Microsoft Research Redmond
2 shared publications - Michel Galley
Microsoft
2 shared publications Xiao Yu
Columbia University Microsoft Research
2 shared publicationsZhou Yu
Columbia University Microsoft Research
2 shared publicationsDong Yu
Tencent AI Lab
1 shared publication- Haitao Mi
Tencent AI Lab
1 shared publication
Latest Publications
- Open Access
Teaching Language Models to Self-Improve through Interactive Demonstrations
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and difficult to learn for smaller models, thus widening the performance gap between state-of-the-art LLMs and more cost-effective and faster ones. To reduce this gap, we introduce TriPosT, a training algorithm that endows smaller models with such self-improvement ability, and show that our approach can improve a LLaMA-7b's performance on math and reasoning tasks by up to 7.13%. In contrast to prior work, we achieve this by using the smaller model to interact with LLMs to collect feedback and improvements on its own generations. We then replay this experience to train the small model. Our experiments on four math and reasoning datasets show that the interactive experience of learning from and correcting its own mistakes is crucial for small models to improve their performance.
Open AccessTeaching Language Models to Self-Improve through Interactive Demonstrations
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and difficult to learn for smaller models, thus widening the performance gap between state-of-the-art LLMs and more cost-effective and faster ones. To reduce this gap, we introduce TriPosT, a training algorithm that endows smaller models with such self-improvement ability, and show that our approach can improve a LLaMA-7b's performance on math and reasoning tasks by up to 7.13%. In contrast to prior work, we achieve this by using the smaller model to interact with LLMs to collect feedback and improvements on its own generations. We then replay this experience to train the small model. Our experiments on four math and reasoning datasets show that the interactive experience of learning from and correcting its own mistakes is crucial for small models to improve their performance.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5127-5149
Teaching Language Models to Self-Improve through Interactive Demonstrations
Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5127-5149
Open AccessTeaching Language Models to Self-Improve through Interactive Demonstrations
Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- Open Access
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities, such as reward hacking and catastrophic forgetting. In this technical report, we propose two innovations to stabilize RLHF training: 1) Advantage Model, which directly models advantage score i.e., extra reward compared to the expected rewards and regulates score distributions across tasks to prevent reward hacking. 2) Selective Rehearsal, which mitigates catastrophic forgetting by strategically selecting data for PPO training and knowledge rehearsing. Our experimental analysis on public and proprietary datasets reveals that the proposed methods not only increase stability in RLHF training but also achieve higher reward scores and win rates.
Open AccessStabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities, such as reward hacking and catastrophic forgetting. In this technical report, we propose two innovations to stabilize RLHF training: 1) Advantage Model, which directly models advantage score i.e., extra reward compared to the expected rewards and regulates score distributions across tasks to prevent reward hacking. 2) Selective Rehearsal, which mitigates catastrophic forgetting by strategically selecting data for PPO training and knowledge rehearsing. Our experimental analysis on public and proprietary datasets reveals that the proposed methods not only increase stability in RLHF training but also achieve higher reward scores and win rates.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 13348-13369
SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 13348-13369
Top Cited PapersOpen AccessSGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.