conftrace_

Robert Kirk

9 papers · 2024–2026 · 4 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

+3 more ↓

🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (3) 🏆 Grand Slam

👑 Triple Crown ❓ The Questioner ⚡ Prolific Year (5)

Conferences

ICLR (4) ICML (3) AAAI (1) NIPS (1)

Top co-authors

Tim Rocktäschel (3) Edward Grefenstette (3) David Krueger (2) Roberta Raileanu (2) Laura Ruis (2) Eric Hambro (2) Aengus Lynch (2) Hidenori Tanaka (1) Juhan Bae (1) Adam Gleave (1)

Keywords

model interpretability (1) adversarial attack (1) language model (1) steering vector (1) few-shot prompting (1) inference-time intervention (1) large language model (1) safeguard pipeline (1)

Papers

STACK: Adversarial Attacks on LLM Safeguard Pipelines AAAI 2026 Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models ICLR 2025 How Do Large Language Monkeys Get Their Power (Laws)? ICML 2025 Investigating Non-Transitivity in LLM-as-a-Judge ICML 2025 Analysing the Generalisation and Reliability of Steering Vectors NIPS 2024 Generalization to New Sequential Decision Making Tasks with In-Context Learning ICML 2024 Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks ICLR 2024 Reward Model Ensembles Help Mitigate Overoptimization ICLR 2024 Understanding the Effects of RLHF on LLM Generalisation and Diversity ICLR 2024