A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
Naaman Tan, Josef Valvoda, Tianyu Liu, Anej Svete, Yanxia Qin, Min-Yen Kan, Ryan Cotterell
- Anthology ID:
- 2024.emnlp-main.822
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14805–14829
- Language:
- URL:
- https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.emnlp-main.822/
- DOI:
- 10.18653/v1/2024.emnlp-main.822
- Cite (ACL):
- Naaman Tan, Josef Valvoda, Tianyu Liu, Anej Svete, Yanxia Qin, Min-Yen Kan, and Ryan Cotterell. 2024. A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14805–14829, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors (Tan et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.emnlp-main.822.pdf