AAAI

Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes

Note2Chat: 通过医疗笔记提升LLM在多轮临床病史采集中的表现

Yang Zhou, Zhenting Sheng, Mingrui Tan, Yuting Song, Jun Zhou, Yu Heng Kwan, Lian Leng Low, Yang Bai, Yong Liu

AI总结 Note2Chat通过医疗笔记训练LLM提升多轮临床病史采集的准确性和效率

Comments Accepted at AAAI-26

LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models

LAMP: 通过预训练模型学习通用对抗扰动以实现多图像任务

Alvi Md Ishmam, Najibul Haque Sarker, Zaber Ibn Abdul Hakim, Chris Thomas

AI总结 LAMP通过预训练模型学习通用对抗扰动，针对多图像多模态大语言模型实现高效的黑盒攻击，提升了多任务攻击成功率。

Comments Accepted in main technical track AAAI 2026

Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation

通过LLM引导的实例生成和渐进适应弥合合成与现实路由问题

Jianghan Zhu, Yaoxin Wu, Zhuoyi Lin, Zhengyuan Zhang, Haiyan Yin, Zhiguang Cao, Senthilnath Jayavelu, Xiaoli Li

机构 * A*STAR（新加坡科技研究局） 纠错

AI总结 通过LLM引导的实例生成和渐进适应方法，提升神经求解器在现实路由问题中的泛化能力。

Comments 21 pages; Published in AAAI 2026, Main Technical Track

Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance

引导扰动敏感性（GPS）：通过嵌入稳定性与词重要性检测对抗文本

Bryan E. Tuck, Rakesh M. Verma

机构 * University of Houston（休斯顿大学） 纠错

AI总结 GPS通过嵌入稳定性与词重要性检测对抗文本，实现高准确率和低计算成本的攻击识别。

Comments 19 pages, 19 figures, 8 tables. Accepted to AAAI 2026. Code available at https://github.com/ReDASers/Guided-Perturbation-Sensitivity