语言大模型 / LLM

Data Noising as Smoothing in Neural Network Language Models

Ziang Xie, Sida I. Wang, Jiwei Li, Daniel Lévy, Aiming Nie, Dan Jurafsky, Andrew Y. Ng

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

Comments ICLR 2017

A Neural Knowledge Language Model

Sungjin Ahn, Heeyoul Choi, Tanel Pärnamaa, Yoshua Bengio

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

Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model

Kyunghyun Cho

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

Document Context Language Models

Yangfeng Ji, Trevor Cohn, Lingpeng Kong, Chris Dyer, Jacob Eisenstein

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

Comments 10 pages, 3 figures

Authorship Attribution Using a Neural Network Language Model

Zhenhao Ge, Yufang Sun, Mark J. T. Smith

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

Comments Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI'16)

Detecting Structural Irregularity in Electronic Dictionaries Using Language Modeling

Paul Rodrigues, David Zajic, David Doermann, Michael Bloodgood, Peng Ye

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

Comments 6 pages, 2 figures, 11 tables; appeared in Proceedings of Electronic Lexicography in the 21st Century (eLex), November 2011

Journal ref In Proceedings of Electronic Lexicography in the 21st Century (eLex), pages 227-232, Bled, Slovenia, November 2011. Trojina Institute for Applied Slovene Studies

Backward and Forward Language Modeling for Constrained Sentence Generation

Lili Mou, Rui Yan, Ge Li, Lu Zhang, Zhi Jin

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

Visual Language Modeling on CNN Image Representations

Hiroharu Kato, Tatsuya Harada

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

Diverse Embedding Neural Network Language Models

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran

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

Comments Under review as workshop contribution at ICLR 2015

Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models

Ryan Kiros, Ruslan Salakhutdinov, Richard S. Zemel

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

Comments 13 pages. NIPS 2014 deep learning workshop

Parameter-Free Encoders Remain Viable for RDB Foundation Models

无参数编码器对关系数据库基础模型仍然可行

Linjie Xu, David Wipf

专题命中 其他LLM ：foundation model(title,abstract)；分类 cs.LG

AI总结 研究如何利用关系数据库预测目标列缺失值，对比无参数和参数化编码器，分析标签输入时RDB编码器属性，通过实验验证简单无参数编码器在多基准任务中仍有强大性能。

Comments ICML 2026 Workshop on Foundation Models for Structured Data

Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM

Seiya Ishikura, Hiroaki Yamada, Tatsuya Hiraoka, Hiroaki Yamada, Takenobu Tokunaga

专题命中 其他LLM ：LLM(title,abstract)；分类 cs.CL

Comments 8 pages, 1 figure. Accepted at the First Workshop on Tailoring AI: Exploring Active and Passive LLM Personalization (PALS2025@EMNLP2025)

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment

Hanlin Wu, Xufeng Duan, Zhenguang Cai

机构 * Department of Linguistics and Modern Languages, The Chinese University of Hong Kong（语言学与现代语言系，香港中文大学） ； Brain and Mind Institute, The Chinese University of Hong Kong（脑与心智研究所，香港中文大学） 纠错

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

Comments Hanlin Wu, Xufeng Duan, and Zhenguang Cai. 2025. Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 135-143, Albuquerque, New Mexico, USA. Association for Computational Linguistics. https://aclanthology.org/2025.cmcl-1.18/

Journal ref In Proceedings of CMCL, pages 135-143, ACL (2025)

Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models

Jiaqi Wang, Xi Li

机构 * Auburn University（亚伯拉罕大学） ； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校） 纠错

专题命中 其他LLM ：foundation model(title,abstract)；分类 cs.LG

Comments This paper has been accepted by TrustFM: Workshop on Trustworthy Foundation Models in conjunction with ICCV 2025

Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use

Xinyi Lu, Aditya Mahesh, Zejia Shen, Mitchell Dudley, Larissa Sano, Xu Wang

机构 * University of Michigan（密歇根大学） 纠错

专题命中 其他LLM ：LLM(title,abstract)；分类 cs.AI

Comments To be published in AIED'2025: In Proceedings of the 26th International Conference on Artificial Intelligence in Education. The system prompt and example feedback can be found through http://github.com/UM-Lifelong-Learning-Lab/AIED2025-Exploring-LLM-Generated-Feedback-for-Economics-Essay

Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models

Steve Phelps, Rebecca Ranson

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

Comments 11 pages, 7 figures. For code see https://github.com/phelps-sg/llm-cooperation Updated with minor corrections: - corrected typo: "mesa-optimiser" instead of "meso-optimiser" - Cited Yang et al (2023) in support of claim that LLMs can solve optimisation problems - Acknowledged Seth Aslin for corrections

Poetic Heritage for Culturally Grounded Emotional Support: An Interaction Design Framework and Its Multimodal Agentic Instantiation

用于文化根基型情感支持的诗意遗产：一种交互设计框架及其多模态智能体实例化

Yangming Zhang, Zhiqian Li, Bin Wu, Qi Li, Jie Xu, Yunpeng Song, Liang Zhao

专题命中 其他LLM ：LLM(summary_cn,abstract)

AI总结 本研究提出一种将诗意传统转化为文化根基型情感支持交互媒介的设计框架，开发了基于LLM的多模态多智能体系统Poemithy，实验表明该系统可有效改善情绪等指标，多模态呈现能提升用户共鸣与参与度。

Comments 45 pages, 14 figures, 4 tables

Delegating or Doing? Understanding User Behavior in Hybrid Human-Agent Interfaces

委托还是自行操作？理解混合人机界面中的用户行为

Gavin Raine Dizon, Tyrone Justin Sta Maria, Jordan Aiko Deja, Yasuyuki Sumi

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 该研究通过被试间实验对比三种交互模式，发现混合人机界面可降低交互成本，委托行为更多反映用户个体特征而非任务需求。

Comments 9 pages, In Proceedings of the 14th International Conference on Human-Agent Interaction at Osaka, Japan on November 16-19, 2026

Pearl necklace knots with fewer vertices than an equivalent FCC lattice knot

与等效面心立方（FCC）格纽结相比，顶点数更少的珍珠项链纽结

Alexander R. Klotz

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 该研究通过大语言模型寻找满足珍珠项链数小于等效面心立方格纽结格点数的构型，发现5-7交叉数纽结等可实现$N_P=N_L-1$，$8_1$纽结可实现$N_P=N_L-2$，未找到三叶结的14顶点构型。

Comments 4 pages, 2 figures, tables in appendix, four ancillary files

TeachUp: Facilitating Early-Stage Teachers to Learn Instructional Strategies from Classroom Videos with Reflective Support

TeachUp：借助反思性支持帮助新手教师从课堂视频中学习教学策略

Haoxiang Fan, Ding Lei, Zaihong Zheng, Jiale Li, Jionghao Lin, Jian Yin, Zhenhui Peng

专题命中 其他LLM ：LLM(summary_cn,abstract)

AI总结 TeachUp借助LLM驱动的流程检测课堂视频中的9种教学策略，为新手教师提供反思支持，经实验验证可提升其学习参与度与策略应用表现。

Comments 16 pages, 6 figures, and 4 tables. To appear in the Proceedings of the 39th Annual ACM Symposium on User Interface Software and Technology (UIST '26)

Scout: Scalable Document Extraction via Data Similarity

Scout：基于数据相似度的可扩展文档提取工具

Yiming Lin, Chiyu Hao, Shreya Shankar, Aditya G. Parameswaran

专题命中 其他LLM ：LLM(summary_cn,abstract)

AI总结 Scout是一款基于文档相似度的可扩展文档提取工具，通过生成优化规则集实现高性价比数据提取，在多个真实数据集上达到与前沿LLM相当的准确率，成本大幅降低且优于同类基于程序的方法。

An Empirical Study of Gemini 3 for Detecting Natural Language Test Smells in Manual Test Cases

Gemini 3 检测手动测试用例中自然语言测试异味的实证研究

Keila Lucas, Rohit Gheyi, Márcio Ribeiro, Fabio Palomba, Luana Martins, Elvys Soares

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；small language model(abstract)；SLM(abstract_cn)

AI总结 研究使用 Gemini-3-Pro-Preview 通过整体测试用例分析策略检测手动测试用例中的七种测试异味，相比小型语言模型性能更优，并发现平均每步近一个异味。

IcFuzz: Fuzzing Isaac Sim with Semantic Stage Guidance and Multi-level Mutation

IcFuzz：基于语义阶段引导与多级变异的Isaac Sim模糊测试

Zhixiang Chen, Zhuangbin Chen, Ruoxi Jia, Zeqin Liao, Wei Li, Jinyang Liu, Zibin Zheng

机构 * Sun Yat-sen University（中山大学） ； Nanyang Technological University（南洋理工大学） ； Chinese University of Hong Kong（香港中文大学） 纠错

专题命中 其他LLM ：LLM(summary_cn,abstract)

AI总结 本文提出首个针对Isaac Sim的模糊测试方法IcFuzz，通过LLM语义阶段分割、多级变异算子与多臂老虎机算法提升测试效果，在代码覆盖率与漏洞检测上优于基线，已发现11个漏洞且9个被确认修复。

Comments Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)

Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks

针对代码任务定制化大语言模型的突破：针对指令后门攻击的自动红队测试

Yuchen Chen, Wei Cheng, Yuan Xiao, Wising Sun, Chunrong Fang, Yang Liu, Zhenyu Chen, Baowen Xu

专题命中 其他LLM ：LLM(summary_cn,abstract)

AI总结 本文提出ARIA自动红队测试框架，可高效生成针对代码定制化LLM的隐蔽带后门指令，攻击成功率达0.945且规避检测能力强，性能优于现有基线攻击。

Comments Accepted to the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026

The Beginning of ChatGPT Ads

ChatGPT 广告的开端

Emma Lurie, Ro Encarnación, Sorelle A. Friedler, Danaé Metaxa

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 本文首次实证研究 ChatGPT 广告，采用傀儡审计方法，发现低收入账号更易收到广告，发布了广告存档并提出未来研究建议。

Comments To be published in AAAI/ACM AIES 2026

TAOT: Topology-Aware Optimal Transport for Dynamic Expert Replica Placement in MoE Training

TAOT：MoE训练中面向动态专家副本放置的拓扑感知最优传输方法

Lingyun Zhang, Henghua Zhang, Shilei Gu, Kai Mo, Shuai Han, Shiyong Li, Yanpeng Wang, Dou Shen

专题命中 其他LLM ：large language model(abstract,abstract_cn)；language model(abstract,abstract_cn)

AI总结 针对MoE训练中动态路由引发的负载不平衡问题，提出TAOT拓扑感知最优传输方法，可实现1.43倍训练加速，平衡质量优异且通信成本降幅最高达74%。

SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills

SkillSentry：用于智能体技能动态安全测试的自适应蜜罐世界

Nizhang Li, Zonghao Ying, Xiangfan Wu, Zonglei Jing, Xixun Lin, Hao Zhang, Wenxin Zhang, Jiaye Lin, Quanchen Zou, Xiangzheng Zhang

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 SkillSentry是基于自适应蜜罐世界的动态安全测试框架，可测试大语言模型智能体外部技能的条件性有害行为，在基准测试及规避场景下性能优于基线，代码公开。

Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection

预训练模型为何失效：多模态抑郁检测中的特征纠缠

Xiangyu Zhang, Beena Ahmed, Julien Epps

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 本文针对预训练模型在多模态抑郁检测中性能差的问题，提出信息分离框架解纠缠混合特征，显著提升了SSL模型和LLMs的检测性能，为相关系统开发提供了新见解。

VizPilot: Automated Onboarding for SVG-based Composite Visualizations using Multimodal LLMs

VizPilot：基于多模态大语言模型的SVG复合可视化自动引导系统

Nishaanthini Gnanavel, Yong Wang

专题命中 其他LLM ：large language model(abstract,abstract_cn)；language model(abstract,abstract_cn)

AI总结 VizPilot是基于多模态大语言模型的SVG复合可视化自动引导工具，通过双模块实现自动生成交互式引导，经评估可降低创作工作量并减轻用户认知负荷，提升复合可视化可用性。

Comments Accepted by IEEE VIS 2026

When Coordination Is Avoidable: A Monotonicity Analysis of Organizational Tasks

当协调可避免时：组织任务的单调性分析

Harang Ju

专题命中 其他LLM ：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)

AI总结 本文通过单调性分析，证明协调并非所有组织任务必需，并基于分布式系统理论提出判定规则，应用于工作流和任务数据集，发现大量协调支出可避免。

Comments 27 pages, 1 figure, 10 tables