Rachel Dias
Rachel Dias has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Alec Helyar, Amelia Glaese, Andrea Vallone.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 161 times in our library · ⭐ Paper Stars ranking: #6456
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 workInformation Systems · 1 work
🧭 Topics 3Research subjects and languages the work is about.Bias, fairness & safety · 1 workLanguage models & pretraining · 1 workReasoning · 1 work
Works by year
2020s
Papers
- Deliberative Alignment: Reasoning Enables Safer Language Models (2024 · 115 citations)
Conventional safety training (SFT, RLHF) has two weaknesses. LLMs answer instantly without deliberating, and they infer safety rules only indirectly from labeled examples. As a result, they can be jailbroken yet still refuse harmless requests. OpenAI researchers propose Deliberative Alignment, which teaches the model… - PaperBench: Evaluating AI's Ability to Replicate AI Research (2025 · 86 citations)
PaperBench measures whether AI agents can independently reproduce recent machine learning research. Agents receive 20 Spotlight and Oral papers from ICML 2024, covering 12 topic areas. For each paper, an agent must write a complete codebase from scratch, without access to the authors' original code, and include a…
Co-authors here
- Alec Helyar
- Amelia Glaese
- Andrea Vallone
- Boaz Barak
- Dane Sherburn
- Eric Wallace
- Evan Mays
- Giulio Starace
- Hyung Won Chung
- James Aung
- Jason Wei
- Johannes Heidecke
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/rachel-dias/