Skip to content

Author

David Williams-King

We have 6 of 38 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Open access Sep 2026

Representation Control for Large Language Models: Survey and Research Challenges

Large language models (LLMs) are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation Control (RepControl) seeks to resolve this problem through targeted interventions that modify high-level representations of concepts such as honesty, harmfulness or power-seeking. We forma...

Lukasz Bartoszcze, Sarthak Munshi, Bryan Sukidi et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Activation Flow: Manufacturing Activations for Steering

Activation Flow (ActFlow), which manufactures activations from correct labels without fine-tuning, scores higher than the smallest-norm rule in 16 of the 18 combinations of locked model and $k, and its steering direction is nearly orthogonal to the honest difference-in-means direction.

Hong-Fu Tan, Linh Le, David Williams-King · 0 citations
#artificial intelligence Preprint Apr 2026

Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning

MANTA, a benchmark of 1,088 five-turn conversations progressing from an implicit Turn-1 scenario through an explicit welfare prompt to three adversarial pressure rounds drawn from a five-type taxonomy, shows welfare robustness depends jointly on the animal and pressure applied.

Isabella Luong, Joy Chen, Sankalpa Ghose et al. · 1 citation
#artificial intelligence Preprint Sep 2026

GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis

GPS-Bench is introduced, an evidence-grounded benchmark for governance policy simulation that links policies to relevant actors, actor actions and downstream impacts using legislative records, lobbying disclosures, regulatory documents, corporate filings, economic data and other public evidence.

Linh Le, Melanie Bui, My Chiffon Nguyen et al. · 0 citations
#machine learning Preprint Aug 2026

A Causal Model for Locating and Unlocking Sandbagging in Model Organisms

A causal model of how sandbagging is carried in the residual stream is proposed, which predicts a window of layers, after the last sandbagging write and before the answer commit, in which a single-layer reference graft of the sandbagging axis to its honest value restores the full capability.

Hong-Fu Tan, Linh Le, David Williams-King · 0 citations
#artificial intelligence Preprint Aug 2026

Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities

Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluations that frontier-model governance depends on. The Elicitation Game found that fine-tuning elicits hidden capability from sandbagging model organisms whereas additive activ...

Linh Le, Hong-Fu Tan, David Williams-King · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.