◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Niels Warncke

5 papers hereh-index 3175 citations6 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author1
  • last author1

Across the 2 of 5 papers where every author was matched, so the position is known.

fields
  • cs.CL2
  • cs.LG2
  • cs.AI1

identity via Semantic Scholar / OpenAlex

works on
adapter training 1backdoor mitigation 1bias 1ethical AI 1inoculation prompting 1large language models 1LLM evaluation 1model alignment 1selective generalization 1value leakage 1

From the 2 of 5 linked papers with an AI index.

most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

22 citations · 22 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026★ 22 cited

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Tan, Niels Warncke +5

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting mode…

cs.CL2025

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time

Daniel Tan, Anders Woodruff, Niels Warncke +4

Language model finetuning often results in learning undesirable traits in combination with desired ones. To address this, we propose inoculation prompting: modifying finetuning dat…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.