Amelia Glaese

5 papers · 2021–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

Venues

EMNLP (2) NeurIPS (2) ICML (1)

Top co-authors

Johannes Welbl (2) Sumanth Dathathri (2) John Mellor (2) Jonathan Uesato (2) Po-Sen Huang (2) Geoffrey Irving (2) Lisa Anne Hendricks (2) John Aslanides (2) Nat McAleese (2) Roman Ring (1)

Research topics

Artificial Intelligence (4) Machine Learning (4) Core AI (4) Application Areas (3) Natural Language Processing (2) Reinforcement Learning (1) Applications (1) Core Methods (1) Generation (1) Learning Types (1) Methods (1) Resources & Methods (1)

Keywords

large language model (3) language model (2) harmful content (2) toxicity detection (2) responsible ai (1) bias mitigation (1) reward model (1) safety evaluation (1) red teaming (1) harmful content detection (1) human preference (1) ai agent (1) adversarial testing (1) automatic evaluation (1) model fairness (1) offensive content detection (1) model bia (1) toxicity mitigation (1) offensive content (1) llm-based judge (1)

Papers

PaperBench: Evaluating AI’s Ability to Replicate AI Research ICML 2025 Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models NeurIPS 2022 Fine-tuning language models to find agreement among humans with diverse preferences NeurIPS 2022 Red Teaming Language Models with Language Models EMNLP 2022 Challenges in Detoxifying Language Models EMNLP 2021