D. Song

发表论文 21 篇 · 总被引 109 次 · h-index 6

代表论文

• Agent Instructs Large Language Models to be General Zero-Shot Reasoners (2023 · arXiv.org · 被引 46)
• COSMIC: Generalized Refusal Direction Identification in LLM Activations (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 21)
• A Framework for Formalizing LLM Agent Security (2026 · arXiv.org · 被引 17)
• Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study (2024 · arXiv.org · 被引 12)
• Peer-Preservation in Frontier Models (2026 · arXiv.org · 被引 11)
• S TEERING S AFETY : A S YSTEMATIC S AFETY E VALUA - TION F RAMEWORK OF R EPRESENTATION S TEERING IN LLM S (被引 11)