ACL

How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains

大型推理模型的置信度估计有多可靠？对高风险领域的系统基准测试

Reza Khanmohammadi, Erfan Miahi, Simerjot Kaur, Ivan Brugere, Charese H. Smiley, Kundan Thind, Mohammad M. Ghassemi

AI总结 本文通过系统基准测试，评估了大型推理模型置信度估计方法的可靠性，发现基于文本的编码器在歧视方面表现最佳，而结构感知模型在校准方面表现最佳，揭示了当前方法的局限性。

Comments Accepted to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026) main conference

Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach

临床文本中的时间关系抽取：一种基于跨度的图变换器方法

Rochana Chaturvedi, Peyman Baghershahi, Sourav Medya, Barbara Di Eugenio

AI总结 本文提出GRAPHTREX方法，通过结合基于跨度的实体关系抽取、临床预训练语言模型和异构图变换器，提升临床文本中时间关系抽取的准确率和长距离关系识别能力。

Comments Introducing a novel method for joint extraction of medical events and temporal relations from free-text, leveraging clinical LPLMs and Heterogeneous Graph Transformers, achieving a 5.5% improvement over the previous state-of-the-art and up to 8.9% on long-range relations

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)