Dawn Song
14 papers · 8928 citations
Most-cited papers
- Measuring Massive Multitask Language Understanding2020 · 7766 citations
- Representation Engineering: A Top-down Approach To AI Transparency2023 · 899 citations
- Rigorllm: Resilient Guardrails For Large Language Models Against Undesired Content2024 · 76 citations
- Guardagent: Safeguard LLM Agents By A Guard Agent Via Knowledge-enabled Reasoning2024 · 73 citations
- Decoding Compressed Trust: Scrutinizing The Trustworthiness Of Efficient Llms Under Compression2024 · 54 citations
- VERINA: Benchmarking Verifiable Code Generation2025
- Opensage: Self-programming Agent Generation Engine2026
- CUBE: A Standard For Unifying Agent Benchmarks2026
- Devops-gym: Benchmarking AI Agents In Software Devops Cycle2026
Topics