Barbara Plank
@barbaraplank.bsky.social
520 followers
160 following
31 posts
Prof, Chair for AI & Computational Linguistics,
Head of MaiNLP lab @mainlp.bsky.social, LMU Munich
Co-director CIS @cislmu.bsky.social
Visiting Prof ITU Copenhagen @itu.dk
ELLIS Fellow @ellis.eu
Vice-President ACL
PI MCML @munichcenterml.bsky.social
Posts
Media
Videos
Starter Packs
Pinned
Reposted by Barbara Plank
Reposted by Barbara Plank
ACL
@aclmeeting.bsky.social
· Jul 28
Reposted by Barbara Plank
Reposted by Barbara Plank
Reposted by Barbara Plank
ACL
@aclmeeting.bsky.social
· Jul 27
Barbara Plank
@barbaraplank.bsky.social
· Jun 20
Barbara Plank
@barbaraplank.bsky.social
· May 20
Reposted by Barbara Plank
Reposted by Barbara Plank
Barbara Plank
@barbaraplank.bsky.social
· Apr 23
Barbara Plank
@barbaraplank.bsky.social
· Apr 15
Barbara Plank
@barbaraplank.bsky.social
· Apr 23
Barbara Plank
@barbaraplank.bsky.social
· Apr 15
Barbara Plank
@barbaraplank.bsky.social
· Apr 15
Barbara Plank
@barbaraplank.bsky.social
· Apr 15
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful advice (e.g."how do ...
arxiv.org
Barbara Plank
@barbaraplank.bsky.social
· Apr 15