zai-org/BPO
Dataset Card for Black-box Prompt Optimization (BPO) Data Summary To advance the development of alignment in language models, we introduce a black-box alignment method. BPO enhances the alignment of various Large Language Models (LLMs) with human preferences using only a plug-and-play model. To further promote alignment work from the prompting perspective, we are releasing the BPO Dataset. This dataset comprises 14,395 entries of prompt optimization pairs, constructed… See the full description on the dataset page: https://huggingface.co/datasets/zai-org/BPO.
| Author / organization | zai-org |
|---|---|
| License (as declared) | apache-2.0 |
| Downloads | 252 (as reported by Hugging Face) |
| Likes | 24 |
| Created | 20 November 2023 |
| Last updated at source | 20 November 2023 |
Recent changes
- 16 Oct 2026 License: none → apache-2.0
- 16 Oct 2026 Description: none → Dataset Card for Black-box Prompt Optimization (BPO) Data Summary To advance the development of alignment in language models, we introduce a black-box alignment method. BPO enhances the alignment of various Large Language Models (LLMs) with
- 16 Oct 2026 Topics added task_categories:text-generation, human_feedback removed transformers, pytorch, llama, text-generation, bpo, thudm, en, text-generation-inference
- 16 Oct 2026 Task: text-generation → none
Changes detected by Silytics between refreshes of the source.
More from zai-org
- zai-org/GLM-5.3-FlashModel
- zai-org/GLM-5.3Model
- zai-org/GLM-OCRModel
- zai-org/GLM-4.7-FlashModel
- zai-org/GLM-5Model
- zai-org/GLM-4.5-AirModel
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.