Scholar

Adam Mahdi

Google Scholar ID: jUDSqzEAAAAJ

Associate Professor, University of Oxford

large language modelsmultimodal AIdigital health

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

1,400

H-index

20

i10-index

30

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

13 items

RepSelect: Robust LLM Unlearning via Representation Selectivity

2026

Cited

0

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

2026

Cited

0

AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI

2026

Cited

0

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

2026

Cited

0

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

2026

Cited

0

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

2025

Cited

0

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

2025

Cited

0

Agentic Reinforcement Learning for Search is Unsafe

2025

Cited

0

Resume (English only)

Research Experience

Research interests include: LLM Evaluation, AI Safety, Mechanistic Interpretability, and Human-LLM Interaction. Extensive research has been conducted in these areas.

Co-authors

0 total

Co-authors: 0 (list not available)