Alec Helyar

Publications by Year

Research Areas

Natural Language Processing Techniques, Safety Systems Engineering in Autonomy, Formal Methods in Verification, Access Control and Trust, Risk and Safety Analysis

Most-Cited Works

• → OpenAI o1 System Card(2024)33 cited
• → Deliberative Alignment: Reasoning Enables Safer Language Models(2025)13 cited
• → Rule Based Rewards for Language Model Safety(2024)2 cited
• → From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training(2025)