🧑🔬 Daojing He — papers of 2025 — 3 papers, the most cited first3 papers · all years of Daojing HeMTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingAnnual Meeting of the Association for Computational Linguistics (ACL)Weiyang Guo, Jing Li, Wenya Wang, et al.2025 · 14 citationsSafety Alignment via Constrained Knowledge UnlearningAnnual Meeting of the Association for Computational Linguistics (ACL)Zesheng Shi, Yucheng Zhou, Jing Li, et al.2025 · 13 citationsNeural Parameter Search for Slimmer Fine-Tuned Models and Better TransferAnnual Meeting of the Association for Computational Linguistics (ACL)Guodong Du, Zitao Fang, Jing Li, et al.2025 · 11 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/daojing-he/year/2025/