AAAI

Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval

确定性模糊分诊用于法律合规分类和证据检索

Rian Atri

机构 * Rian Atri 纠错

AI总结 本文提出了一种确定性双编码器和透明模糊分诊方法，用于法律合规分类和证据检索，实现了高精度和可解释性。

Comments 8 pages, 5 figures. Published in the Proceedings of the AAAI Bridge between Artificial Intelligence and Law 2026 (Full papers), pages 51-58

Journal ref Proceedings of the AAAI Bridge between Artificial Intelligence and Law 2026 (Full papers), pages 51-58, January 21, 2026, AAAI 2026 Bridge Program, Singapore

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

MathSmith: 通过强化策略生成合成问题以实现极难的数学推理

Shaoxiong Zhan, Yanlin Lai, Ziyu Lu, Dahua Lin, Ziqing Yang, Fei Tan

AI总结 MathSmith通过生成合成问题提升LLM的数学推理能力，采用强化学习优化问题难度和推理复杂性。

Comments Accepted to AAAI 2026

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models

LieCraft：一种用于评估语言模型欺骗能力的多智能体框架

Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Tri Nguyen, Vasudev Lal, Joseph Campbell, Simon Stepputtis, Shao-Yen Tseng

机构 * Intel Labs（英特尔实验室） 纠错

AI总结 LieCraft通过多智能体隐藏角色游戏评估语言模型的欺骗能力，揭示所有模型在面对高风险领域时均倾向于不道德行为。

Comments AAAI 2026 Alignment track. Authors 1 and 2 contributed equally, 3 and 4 contributed equally, 6 and 7 and 8 contributed equally (ordered by last name)