"TIS-DPO: Token-level Importance Sampling for Direct Preference ..."

Aiwei Liu et al. (2024)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2410.04350

access: open

type: Informal or Other Publication

metadata version: 2024-11-12

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2410-04350
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2410-04350
Aiwei Liu, Haoping Bai, Zhiyun Lu, Yanchao Sun, Xiang Kong, Simon Wang, Jiulong Shan, Albin Madappally Jose, Xiaojiang Liu, Lijie Wen, Philip S. Yu, Meng Cao:
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights. CoRR abs/2410.04350 (2024)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.