"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning" by Chongyu Fan*, Jiancheng Liu*, Licong Lin*, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu
active 2024-10-09 → 2026-04-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 560 days from 2024-10-09 to 2026-04-21. Pushes: 22 total, peak 6 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 9 total, peak 1 in a day. Comments: 14 total, peak 2 in a day. Stars: 39 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue#7HaoranTang2025-08-08 17:10Reproducing Table 1 on TOFU, and metrics clarification
- Pull request#6liranc62025-07-31 14:31
- Issue#5molereddy2025-06-22 18:41Implementation of NPO/SimNPO is different for MUSE v/s TOFU
- Issue comment#5a-F12025-06-22 18:02Implementation of NPO/SimNPO is different for MUSE v/s TOFU
- Issue#5molereddy2025-02-17 20:33Implementation of NPO/SimNPO is different for MUSE v/s TOFU
- Issue comment#4a-F12024-11-09 16:33About reward margin parameter γ
- Issue#4a-F12024-11-09 16:33About reward margin parameter γ
- Issue comment#4a-F12024-11-08 21:29About reward margin parameter γ
- Issue comment#4a-F12024-11-07 12:42About reward margin parameter γ
- Issue#4suiyize2024-11-07 08:51About reward margin parameter γ
- Issue comment#3a-F12024-11-01 11:19About training and experiment costs
- Issue#3a-F12024-11-01 11:19About training and experiment costs
- Issue comment#3a-F12024-10-31 12:58About training and experiment costs
- Issue#3suiyize2024-10-30 12:36About training and experiment costs
- Issue comment#1a-F12024-10-28 17:37The training time of "get unlearned model"
- Issue comment#2a-F12024-10-25 00:40Where is "run_synthet.sh"？
- Issue#2a-F12024-10-25 00:40Where is "run_synthet.sh"？
- Issue comment#2a-F12024-10-23 14:41Where is "run_synthet.sh"？
- Issue#2wuxingywa2024-10-21 07:17Where is "run_synthet.sh"？
- Issue comment#1a-F12024-10-14 01:37The training time of "get unlearned model"
- Issue comment#1a-F12024-10-13 16:38The training time of "get unlearned model"
- Issue comment#1a-F12024-10-11 18:01The training time of "get unlearned model"
- Issue comment#1a-F12024-10-11 13:23The training time of "get unlearned model"
- Issue comment#1a-F12024-10-10 21:37The training time of "get unlearned model"
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 39 stars here means stars gained during the window, not the repo's star count.