arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Transactions on Machine Learning Research · 期刊 · Machine Learning

2026-04-08 至 2026-04-08 共收录 3
2510.01025 2026-04-08 cs.AI cs.CL

Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling

基于监督多维缩放的LLMs特征流形分析假设

Federico Tiblias, Irina Bigoulaeva, Jingcheng Niu, Simone Balloccu, Iryna Gurevych

机构 * Technical University of Darmstadt(达姆施塔特工业大学) Ubiquitous Knowledge Processing Lab (UKP Lab)(泛在知识处理实验室 (UKP Lab)) National Research Center for Applied Cybersecurity ATHENE(国家应用网络安全研究中心 ATHENE) Zuse School ELIZA, Technical University of Darmstadt(Zuse School ELIZA, 达姆施塔特工业大学)

AI总结 本文提出SMDS方法,通过分析特征流形几何结构揭示语言模型的语义表示机制,发现不同特征呈现不同的几何形态并支持动态推理。

Comments Published in TMLR (March 2026) | OpenReview: https://openreview.net/forum?id=vCKZ40YYPr | Code: https://github.com/UKPLab/tmlr2026-manifold-analysis

Journal ref Transactions on Machine Learning Research (TMLR) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22346 2026-04-08 cs.LG cs.AI

First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution

梯度提升解释中的首 mover 偏差:机制、检测与解决

Drake Caraker, Bryan Arnold, David Rhoads

AI总结 本文探讨了梯度提升中SHAP特征重要性因序列残差拟合导致的首 mover 偏差机制,提出DASH和随机重训练方法可缓解该问题,提升模型稳定性。

Comments v2: 38 pages, 12 tables, 6 figures, 7 appendices. Major revision for TMLR: 50-rep experiments (was 20), crossed ANOVA with F-statistics, FSI quantitative validation, LIME attribution-agnostic demo, 2-tree analytical example, impossibility theorem cross-references, model governance framing. All results from SageMaker ml.g5.16xlarge (64 vCPU). Code: https://github.com/DrakeCaraker/dash-shap

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08528 2026-04-08 cs.CL cs.SD eess.AS

On The Landscape of Spoken Language Models: A Comprehensive Survey

关于语音语言模型的景观:全面综述

Siddhant Arora, Kai-Wei Chang, Chung-Ming Chien, Yifan Peng, Haibin Wu, Yossi Adi, Emmanuel Dupoux, Hung-Yi Lee, Karen Livescu, Shinji Watanabe

机构 * Carnegie Mellon University(卡内基梅隆大学) National Taiwan University(国立台湾大学) Toyota Technological Institute at Chicago(丰田芝加哥技术研究所) Hebrew University of Jerusalem(耶路撒冷希伯来大学) ENS - PSL, EHESS, CNRS(巴黎高等师范学院 - 巴黎文理研究大学、社会科学高等研究院、法国国家科学研究中心)

AI总结 本文综述了语音语言模型的发展,分析了其架构、训练和评估方法,探讨了关键挑战与未来方向。

Comments Published in Transactions on Machine Learning Research

详情

展开后加载摘要…

URL PDF HTML 收藏