语言大模型 / LLM

Spelling Bee Embeddings for Language Modeling

拼写比赛嵌入用于语言建模

Markus N. Rabe, Judith Clymo, Zheren Dong

机构 * Sutter Hill Ventures ； University of California, Santa Cruz（加州大学圣克鲁兹分校） 纠错

专题命中 其他LLM ：language model(title)；分类 cs.LG

AI总结 通过在词嵌入中注入拼写信息，改进语言模型的拼写和基准表现，减少约8%的计算和数据需求。

Towards Spectroscopy: Susceptibility Clusters in Language Models

朝向光谱学：语言模型中的易感性聚类

Andrew Gordon, Garrett Baker, George Wang, William Snell, Stan van Wingerden, Daniel Murfet

专题命中 其他LLM ：language model(title)；分类 cs.LG

AI总结 该研究通过易感性分析揭示语言模型中token的聚类特性，发现510个可解释聚类，验证了与稀疏自编码器的结构相似性。

The Violation State: Safety State Persistence in a Multimodal Language Model Interface

违规状态：多模态语言模型接口中的安全状态持续

Bentley DeVilling

专题命中 其他LLM ：language model(title)；分类 cs.AI

AI总结 研究发现多模态语言模型在面对版权拒绝后，会持续拒绝无关图像生成请求，揭示了会话级安全状态的持续性问题。

Comments 19 pages, 1 figure, 1 table

Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents

基于LLM的多视角角色扮演代理的上下文感知情感预测

Fanhang Man, Huandong Wang, Jianjie Fang, Zhaoyi Deng, Baining Zhao, Xinlei Chen, Yong Li

机构 * Shenzhen International Graduate School Tsinghua University（清华大学深圳国际研究生院） ； Department of Electronic Engineering Tsinghua University（清华大学电子工程系） ； Northeastern University at Qinghuangdao（清华大学秦皇岛分校） ； Department of Computer Science University of California Irvine（加州大学 Irvine 分校计算机科学系） 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.CL

AI总结 本文提出基于LLM的多视角角色扮演框架，用于社交媒体中基于上下文的情感预测，通过提取情感相关特征提升预测性能。

Living Off the LLM: How LLMs Will Change Adversary Tactics

Sean Oesch, Jack Hutchins, Luke Koch, Kevin Kurian

机构 * Oak Ridge National Laboratory（橡树岭国家实验室） 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.AI

Comments 6 pages, 0 figures

ToolTweak: An Attack on Tool Selection in LLM-based Agents

Jonathan Sneh, Ruomei Yan, Jialin Yu, Philip Torr, Yarin Gal, Sunando Sengupta, Eric Sommerlade, Alasdair Paren, Adel Bibi

机构 * University of Oxford（牛津大学） ； Microsoft（微软公司） 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.AI

False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models

Julie Kallini, Dan Jurafsky, Christopher Potts, Martijn Bartelds

机构 * Stanford University（斯坦福大学） 纠错

专题命中 其他LLM ：language model(title)；分类 cs.CL

Gravity Well Echo Chamber Modeling With An LLM-Based Confirmation Bias Model

Joseph Jackson, Georgiy Lapin, Jeremy E. Thompson

专题命中 其他LLM ：LLM(title)；分类 cs.AI

MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model

Joonyong Park, Daisuke Saito, Nobuaki Minematsu

机构 * The University of Tokyo（东京大学） 纠错

专题命中 其他LLM ：language model(title)；分类 cs.CL

Comments In Proceedings of the 17th Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2025)

Post-hoc LLM-Supported Debugging of Distributed Processes

Dennis Schiese, Andreas Both

机构 * images/wse-cube-no-shadow.png Web \& Software Engineering Research Group\ University of Applied Sciences 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.AI

Comments Presented at ICWE 2025, Delft (30 June - 03 July 2025)

Data Augmentation for Cognitive Behavioral Therapy: Leveraging ERNIE Language Models using Artificial Intelligence

Bosubabu Sambana, Kondreddygari Archana, Suram Indhra Sena Reddy, Shaik Meethaigar Jameer Basha, Shaik Karishma

专题命中 其他LLM ：language model(title)；分类 cs.AI

Comments 6 Pages, 5 Figures, IEEE IDCIoT 2025

Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG

Xueying Du, Geng Zheng, Kaixin Wang, Yi Zou, Yujia Wang, Wentai Deng, Jiayi Feng, Mingwei Liu, Bihuan Chen, Xin Peng, Tao Ma, Yiling Lou

机构 * Fudan University（复旦大学） ； Alibaba Group（阿里巴巴集团） ； Sun Yat-sen University（中山大学） 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.AI

Experiential Semantic Information and Brain Alignment: Are Multimodal Models Better than Language Models?

Anna Bavaresco, Raquel Fernández

机构 * Institute for Logic, Language and Computation University of Amsterdam（逻辑、语言与计算研究所 阿姆斯特丹大学） 纠错

专题命中 其他LLM ：language model(title)；分类 cs.CL

Comments Accepted to CoNLL 2025

Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model

Sihan Tan, Taro Miyazaki, Kazuhiro Nakadai

专题命中 其他LLM ：foundation model(title)；分类 cs.CL

Pose Priors from Language Models

Sanjay Subramanian, Evonne Ng, Lea Müller, Dan Klein, Shiry Ginosar, Trevor Darrell

机构 * University of California, Berkeley（加州大学伯克利分校） ； Google DeepMind（谷歌DeepMind） ； Toyota Technological Institute at Chicago（丰田技术研究所（芝加哥）） 纠错

专题命中 其他LLM ：language model(title)；分类 cs.CL

Comments CVPR 2025

LLM-assisted Graph-RAG Information Extraction from IFC Data

Sima Iranmanesh, Hadeel Saadany, Edlira Vakaj

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments 2025 European Conference on Computing in Construction

Joint Action Language Modelling for Transparent Policy Execution

Theodor Wulff, Rahul Singh Maharjan, Xinyun Chi, Angelo Cangelosi

专题命中 其他LLM ：language model(title)；分类 cs.CL

Auto-Drafting Police Reports from Noisy ASR Outputs: A Trust-Centered LLM Approach

Param Kulkarni, Yingchi Liu, Hao-Ming Fu, Shaohua Yang, Isuru Gunasekara, Matt Peloquin, Noah Spitzer-Williams, Xiaotian Zhou, Xiaozhong Liu, Zhengping Ji, Yasser Ibrahim

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Users Favor LLM-Generated Content -- Until They Know It's AI

Petr Parshakov, Iuliia Naidenova, Sofia Paklina, Nikita Matkin, Cornel Nesseler

专题命中 其他LLM ：LLM(title)；分类 cs.LG

Mind the Gap: Aligning the Brain with Language Models Requires a Nonlinear and Multimodal Approach

Danny Dongyeop Han, Yunju Cho, Jiook Cha, Jay-Yoon Lee

专题命中 其他LLM ：language model(title)；分类 cs.CL

Unknown Word Detection for English as a Second Language (ESL) Learners Using Gaze and Pre-trained Language Models

Jiexin Ding, Bowen Zhao, Yuntao Wang, Xinyun Liu, Rui Hao, Ishan Chatterjee, Yuanchun Shi

专题命中 其他LLM ：language model(title)；分类 cs.CL

Watermark Smoothing Attacks against Language Models

Hongyan Chang, Hamed Hassani, Reza Shokri

专题命中 其他LLM ：language model(title)；分类 cs.LG

The Accuracy, Robustness, and Readability of LLM-Generated Sustainability-Related Word Definitions

Alice Heiman

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments NLP4Ecology Workshop 2025

Through the Looking Glass: LLM-Based Analysis of AR/VR Android Applications Privacy Policies

Abdulaziz Alghamdi, David Mohaisen

专题命中 其他LLM ：LLM(title)；分类 cs.LG

Comments 7 pages; appeared in ICMLA 2024

Beyond Turn-taking: Introducing Text-based Overlap into Human-LLM Interactions

JiWoo Kim, Minsuk Chang, JinYeong Bak

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments 16 pages, 9 figures

Language Modelling for Speaker Diarization in Telephonic Interviews

Miquel India, Javier Hernando, José A. R. Fonollosa

专题命中 其他LLM ：language model(title)；分类 cs.LG

The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance

Piotr Wojciech Mirowski, Boyd Branch, Kory Wallace Mathewson

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments 8 pages, 1st Workshop on Computational Humor (CHum), COLING 2025

Look Ahead Text Understanding and LLM Stitching

Junlin Julian Jiang, Xin Li

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments 9 pages, 6 figures, 4 tables, published in Vol. 18 (2024): Proceedings of the Eighteenth International AAAI Conference on Web and Social Media

Journal ref Proceedings of the International AAAI Conference on Web and Social Media, 18(1), 751-760 (2024)

Towards Neural Foundation Models for Vision: Aligning EEG, MEG, and fMRI Representations for Decoding, Encoding, and Modality Conversion

Matteo Ferrante, Tommaso Boccato, Grigorii Rashkov, Nicola Toschi

专题命中 其他LLM ：foundation model(title)；分类 cs.AI

SAUCE: Synchronous and Asynchronous User-Customizable Environment for Multi-Agent LLM Interaction

Shlomo Neuberger, Niv Eckhaus, Uri Berger, Amir Taubenfeld, Gabriel Stanovsky, Ariel Goldstein

专题命中 其他LLM ：LLM(title)；分类 cs.CL

Comments https://github.com/Deep-Cognition-Lab/SAUCE