◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Leo Schwinn

29 papers hereh-index 13789 citations54 works total

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

author position
  • first author4
  • middle author16
  • last author8

Across the 28 of 29 papers where every author was matched, so the position is known.

fields
  • cs.LG16
  • cs.CL4
  • cs.CR4
  • cs.CV4
  • cs.AI1
same name
  • Leo Schwinn — 4 papers, h 2

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20242026
most citedDiffusion LLMs are Natural Adversaries for any LLM

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2026

A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Leo Schwinn, Moritz Ladenburger, Tim Beyer +3

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, thes…

cs.CL2025

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens

David Dobre, Mehrnaz Mofakhami, Sophie Xhonneux +2

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such dis…

cs.CL2025

Jailbreak Distillation: Renewable Safety Benchmarking

Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…

cs.CL2024

Extracting Unlearned Information from LLMs with Activation Steering

Atakan Seyitoğlu, Aleksei Kuvshinov, Leo Schwinn +1

An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or c…

◍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.