Detoxifying Large Language Models via Knowledge Editing (2024 · 84 citations)
Safety-aligned LLMs can still be steered into harmful output when a malicious request is wrapped in a carefully engineered jailbreak prompt. The authors ask whether knowledge editing can fix the specific toxic parts of a model instead of only masking them.
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms (2025 · 14 citations)
The paper addresses how to control LLM behavior at inference time, especially safety, without relying on fragile system prompts.
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026 · 3 citations)
LLMs are increasingly used for interactive fiction, games and co-written stories, yet nobody had systematically checked whether they can convincingly play antagonists.
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics (2026 · 1 citation)
Methods for controlling LLM behaviour are usually studied separately, with different assumptions and evaluation setups.
Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026)
LLMs are increasingly used in consequential settings, but little is known about the values they apply when distributing scarce resources.

Co-authors here

12 of 26 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 75 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 1 November 2026