Sign in

Xinpeng Wang

@xinpeng.bsky.social
67 followers 97 following 1 posts

PhD student @LMU. Eval & LLM Alignment. xinpeng-wang.github.io

PostsRepliesMedia
Reposted by Xinpeng Wang
MaiNLP lab, LMU Munich @mainlp.bsky.social · 24/04/2025
Reunion in Singapore!🇸🇬 @barbaraplank.bsky.social, @xinpeng.bsky.social, who's currently on a research stay at NYU, and Chengzhi are presenting their work at @iclr-conf.bsky.social
2172
Reposted by Xinpeng Wang
Barbara Plank @barbaraplank.bsky.social · 15/04/2025
Upcoming ICLR 2025 paper: ✂️ Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation We propose a surgical & flexible approach to mitigate false refusal in LLMs with minimal effect on performance and inference cost led by @xinpeng.bsky.social (1/2)
192
Reposted by Xinpeng Wang
MaiNLP lab, LMU Munich @mainlp.bsky.social · 01/04/2025
🎉MaiNLP is turning 3 today!🎂🥳 We’ve grown a lot since @barbaraplank.bsky.social started this group with nothing but three aspiring researches and a hand-drawn sign on the door. Huge thanks to all the amazing people who have joined or visited us since. Here’s to many more years of exciting research!🚀
The hand-drawn sign from three years ago.
1199
Xinpeng Wang @xinpeng.bsky.social · 23/01/2025
I’m thrilled to share that our paper on mitigating false refusal in language models has been accepted to ICLR 2025 @iclr-conf.bsky.social! arxiv.org/abs/2410.03415 Joint work with chengzhi, @paul-rottger.bsky.social, @barbaraplank.bsky.social.
082