Francis Rhys Ward

Venues

Frequent coauthors

Papers

1. AI Sandbagging: Language Models can Strategically Underperform on Evaluations
   ICLR 2025 ·

   Teun van der Weij

   DBLP profile ↗ORCID search ↗
2. CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
   NeurIPS 2025 · Francis Ward
3. Higher-Order Belief in Incomplete Information MAIDs
   AAMAS 2025 ·

   Jack Foxabbott

   DBLP profile ↗ORCID search ↗
4. The Elicitation Game: Evaluating Capability Elicitation Techniques
   ICML 2025 ·

   Felix Hofstätter

   DBLP profile ↗ORCID search ↗
5. Towards a Theory of AI Personhood
   AAAI 2025 · Francis Rhys Ward
6. Evaluating Language Model Character Traits
   EMNLP 2024 · Francis Rhys Ward
7. The Reasons that Agents Act: Intention and Instrumental Goals
   AAMAS 2024 · Francis Rhys Ward