UltraFeedback: Boosting Language Models with Scaled AI Feedback
- URL: http://arxiv.org/abs/2310.01377v2
- Date: Tue, 16 Jul 2024 03:24:39 GMT
- Title: UltraFeedback: Boosting Language Models with Scaled AI Feedback
- Authors: Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, Maosong Sun,
- Abstract summary: We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset.
Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
- Score: 99.4633351133207
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in small sizes or limited topics of current datasets. This further hinders feedback learning as well as alignment research within the open-source community. To address this issue, we explore how to go beyond human feedback and collect high-quality \textit{AI feedback} automatically for a scalable alternative. Specifically, we identify \textbf{scale and diversity} as the key factors for feedback data to take effect. Accordingly, we first broaden instructions and responses in both amount and breadth to encompass a wider range of user-assistant interactions. Then, we meticulously apply a series of techniques to mitigate annotation biases for more reliable AI feedback. We finally present \textsc{UltraFeedback}, a large-scale, high-quality, and diversified AI feedback dataset, which contains over 1 million GPT-4 feedback for 250k user-assistant conversations from various aspects. Built upon \textsc{UltraFeedback}, we align a LLaMA-based model by best-of-$n$ sampling and reinforcement learning, demonstrating its exceptional performance on chat benchmarks. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models, serving as a solid foundation for future feedback learning research. Our data and models are available at https://github.com/thunlp/UltraFeedback.
Related papers
- VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment [55.7956150385255]
We investigate the efficacy of AI feedback to scale supervision for aligning vision-language models.
We introduce VLFeedback, the first large-scale vision-language feedback dataset.
We train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback.
arXiv Detail & Related papers (2024-10-12T07:56:47Z) - Learning from Naturally Occurring Feedback [25.266461597402056]
We propose a scalable method for extracting feedback that users naturally include when interacting with chat models.
We manually annotated conversation data to confirm the presence of naturally occurring feedback.
We apply our method to over 1M conversations to obtain hundreds of thousands of feedback samples.
arXiv Detail & Related papers (2024-07-15T17:41:34Z) - Aligning Large Language Models from Self-Reference AI Feedback with one General Principle [61.105703857868775]
We propose a self-reference-based AI feedback framework that enables a 13B Llama2-Chat to provide high-quality feedback.
Specifically, we allow the AI to first respond to the user's instructions, then generate criticism of other answers based on its own response as a reference.
Finally, we determine which answer better fits human preferences according to the criticism.
arXiv Detail & Related papers (2024-06-17T03:51:46Z) - Inverse Constitutional AI: Compressing Preferences into Principles [37.28372419588119]
We look at the Inverse Constitutional AI (ICAI) problem.
In ICAI, a set of principles is used to provide feedback and fine-tune AI models.
We propose an initial ICAI algorithm and validate its generated constitutions.
arXiv Detail & Related papers (2024-06-02T11:54:50Z) - Data-Efficient Alignment of Large Language Models with Human Feedback
Through Natural Language [31.0723480021355]
We investigate data efficiency of modeling human feedback that is in natural language.
We fine-tune an open-source LLM, e.g., Falcon-40B-Instruct, on a relatively small amount of human feedback in natural language.
We show that this model is able to improve the quality of responses from even some of the strongest LLMs.
arXiv Detail & Related papers (2023-11-24T15:20:36Z) - Constructive Large Language Models Alignment with Diverse Feedback [76.9578950893839]
We introduce Constructive and Diverse Feedback (CDF) as a novel method to enhance large language models alignment.
We exploit critique feedback for easy problems, refinement feedback for medium problems, and preference feedback for hard problems.
By training our model with this diversified feedback, we achieve enhanced alignment performance while using less training data.
arXiv Detail & Related papers (2023-10-10T09:20:14Z) - Training Language Models with Language Feedback at Scale [50.70091340506957]
We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback.
ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements.
We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
arXiv Detail & Related papers (2023-03-28T17:04:15Z) - Training Language Models with Natural Language Feedback [51.36137482891037]
We learn from language feedback on model outputs using a three-step learning algorithm.
In synthetic experiments, we first evaluate whether language models accurately incorporate feedback to produce refinements.
Using only 100 samples of human-written feedback, our learning algorithm finetunes a GPT-3 model to roughly human-level summarization.
arXiv Detail & Related papers (2022-04-29T15:06:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.