◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Leonard Dung

6 papers hereh-index 9331 citations48 works total

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

author position
  • first author2
  • middle author2
  • last author2

Across the 6 of 6 papers where every author was matched, so the position is known.

fields
  • cs.AI3
  • cs.CY3

identity via Semantic Scholar / OpenAlex

collaborators
Showing cs.AIShow all

3 papers · 1 filter

cs.AI2026

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

Valen Tagliabue, Leonard Dung

We develop new experimental paradigms for measuring welfare in language models. We compare verbal reports of models about their preferences with preferences expressed through behav…

cs.AI2026

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

Jonas Wiedermann-Möller, Leonard Dung, Maksym Andriushchenko

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to…

cs.AI2025

AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?

Leonard Dung, Florian Mai

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which th…

◍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.