语言大模型 / LLM

Paraphrase Detection: Human vs. Machine Content

Jonas Becker, Jan Philip Wahle, Terry Ruas, Bela Gipp

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

Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization

Canwen Xu, Julian McAuley, Penghan Wang

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

Comments The Web Conference (WWW 2023) Demo

Attention-likelihood relationship in transformers

Valeria Ruscio, Valentino Maiorca, Fabrizio Silvestri

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

ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions

Deyao Zhu, Jun Chen, Kilichbek Haydarov, Xiaoqian Shen, Wenxuan Zhang, Mohamed Elhoseiny

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

From Copilot to Pilot: Towards AI Supported Software Development

Rohith Pudari, Neil A. Ernst

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

Machine Learning Model Attribution Challenge

Elizabeth Merkhofer, Deepesh Chaudhari, Hyrum S. Anderson, Keith Manville, Lily Wong, João Gante

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

Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models

Hyeonho Jeong, Gihyun Kwon, Jong Chul Ye

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

Witscript 2: A System for Generating Improvised Jokes Without Wordplay

Joe Toplyn

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

Comments 5 pages. Published in the Proceedings of the 13th International Conference on Computational Creativity (ICCC 2022), pages 54-58. arXiv admin note: text overlap with arXiv:2301.02695. substantial text overlap with arXiv:2302.02008

Coder Reviewer Reranking for Code Generation

Tianyi Zhang, Tao Yu, Tatsunori B. Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I. Wang

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

Data Governance in the Age of Large-Scale Data-Driven Language Technology

Yacine Jernite, Huu Nguyen, Stella Biderman, Anna Rogers, Maraim Masoud, Valentin Danchev, Samson Tan, Alexandra Sasha Luccioni, Nishant Subramani, Gérard Dupont, Jesse Dodge, Kyle Lo, Zeerak Talat, Isaac Johnson, Dragomir Radev, Somaieh Nikpoor, Jörg Frohberg, Aaron Gokaslan, Peter Henderson, Rishi Bommasani, Margaret Mitchell

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

Comments 32 pages: Full paper and Appendices; Association for Computing Machinery, New York, NY, USA, 2206-2222

Journal ref Proceedings of 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT '22)

Re3: Generating Longer Stories With Recursive Reprompting and Revision

Kevin Yang, Yuandong Tian, Nanyun Peng, Dan Klein

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

Comments EMNLP 2022

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander I. Rudnicky

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

Comments Accepted at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). The first two authors contributed equally to this work

Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals

Thilo Hagendorff, Leonie Bossert, Tse Yip Fai, Peter Singer

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

Putting GPT-3's Creativity to the (Alternative Uses) Test

Claire Stevenson, Iris Smal, Matthijs Baas, Raoul Grasman, Han van der Maas

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

Comments 5 pages, 6 figures, accepted at the International Conference on Computational Creativity (ICCC) 2022 as a Short Paper. See https://osf.io/vmk3c/ for data, analyses and code

What GPT Knows About Who is Who

Xiaohan Yang, Eduardo Peynetti, Vasco Meerman, Chris Tanner

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

Comments Accepted by ACL 2022 Workshop on Insights from Negative Results in NLP

Semantic features of object concepts generated with GPT-3

Hannes Hansen, Martin N. Hebart

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

CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems

Fei Mi, Yitong Li, Yasheng Wang, Xin Jiang, Qun Liu

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

Comments Accepted at AAAI2022

Natural-Language Multi-Agent Simulations of Argumentative Opinion Dynamics

Gregor Betz

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

Salience-Aware Event Chain Modeling for Narrative Understanding

Xiyang Zhang, Muhao Chen, Jonathan May

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

Comments EMNLP 2021

Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes

Tomasz Limisiewicz, David Mareček

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

Comments EMNLP 2021 Main Conference

Staircase Attention for Recurrent Processing of Sequences

Da Ju, Stephen Roller, Sainbayar Sukhbaatar, Jason Weston

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

OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation

Phuc D. A. Nguyen, Minh Luu, Anh Tran, Cuong Pham, Khoi Nguyen

机构 * Movian AI ； Posts & Telecommunications Inst. of Tech（电信技术研究所） 纠错

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

Comments Accepted at ICCVW'25 - OpenSUN3D: 5th Workshop on Open-World 3D Scene Understanding with Foundation Models

LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment

Yifei Liu, Hengwei Ye, Shuhang Li

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

Comments The result is no longer believeable. Teaching force issue exists in the infer time of LLM

Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors

Yi-Fan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan, Rong Jin

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

Comments 8 pages, 3 figures, AAAI 2024 Workshop on Responsible Language Models

From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction

从错误报告到浏览器可执行流程：一种大语言模型驱动的Web GUI错误复现智能体

Cunming Zhang, Yu Pei, Michail Papadakis

专题命中 其他LLM ：LLM(title)

AI总结 本文提出ReBug智能体系统，通过分阶段驱动真实浏览器复现Web GUI错误，在667条真实报告上的评估显示其性能优于基线，可有效支持基于报告的浏览器错误复现。

Comments 13 pages, 1 figure

Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations

网络化生成代理中的涌现协调行为：信息操作的战略动态建模

Gian Marco Orlando, Jinyi Ye, Valerio La Gatta, Mahdi Saeedi, Vincenzo Moscato, Emilio Ferrara, Luca Luceri

专题命中 其他LLM ：LLM(title)

AI总结 本文研究了生成代理在模拟信息操作中的协调行为，发现通过共享目标即可实现接近人工协调的水平，揭示了自动化信息操作的社会风险。

Journal ref WWW '26: Proceedings of the ACM Web Conference 2026

LLM-Guided Program Evolution for Targeted Black-Box Attacks on Perceptual Hash Algorithms

用于对感知哈希算法进行有针对性的黑盒攻击的大语言模型引导的程序进化

A. Krylov, D. Rakhov, V. Veselova, D. Bolokhov, Oleg Y. Rogov

专题命中 其他LLM ：LLM(title)

AI总结 研究针对感知哈希算法的黑盒攻击，提出基于GigaEvo和OpenEvolve的进化框架，通过综合分数评估攻击性能，实验表明该方法在减少查询次数、降低L2失真方面优于现有基线，揭示了相关漏洞并推动鲁棒方案开发。

Comments 15 pages, 2 figures, 9 tables

Anomalous Frame Detection by Grouping Frame Similarities between Two Videos Computed by Vision-Language Model to Extract Expert Workers' Unique Actions

通过对视觉语言模型计算的两个视频之间的帧相似性进行分组来检测异常帧，以提取专家工人的独特动作

Ryo Sakai, Yongpeng Cao, Nobutaka Kimura

专题命中 其他LLM ：language model(title)

AI总结 针对熟练维护工人减少的问题，提出通过比较两个视频帧相似性检测异常帧来提取专家独特动作的方法，在模拟实验中对特定动作类型提取率达66.9%，比传统技术提高50个百分点，有助于技能转移和劳动力发展。

Comments 11 pages, 6 figures, 2 tables

From Prompting to Verification: How Experience Shapes Vibe Coding Practices

从提示到验证：经验如何塑造Vibe编码实践

Ahmed Fawzy, Amjed Tahir, Kelly Blincoe

专题命中 其他LLM ：prompting(title)

AI总结 通过调查162名不同经验水平的Vibe编码者，发现经验选择性影响编码动机、交互方式和质量保证实践，存在感知-行动差距：对AI生成代码风险的认识普遍，但评估、调试和验证能力依赖于经验。

Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics

骨干即一切：评估冻结基础模型在合成图像鉴伪中的脆弱性

Chiara Musso, Joy Battocchio, Andrea Montibeller, Giulia Boato

机构 * University of Trento（特伦托大学） 纠错

专题命中 其他LLM ：foundation model(title)

AI总结 本文提出SIAA攻击方法，通过仅利用检测器的ViT骨干知识，在目标检测器的特征空间内生成高效对抗样本，揭示了冻结基础模型在对抗多媒体鉴伪中的脆弱性。