语言大模型 / LLM - arXivDaily 专题

2410.22284 2024-10-30 cs.CR cs.LG 77%

Embedding-based classifiers can detect prompt injection attacks

Md. Ahsan Ayub, Subhabrata Majumdar

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

2410.21620 2024-10-30 cs.AI 77%

Asynchronous Tool Usage for Real-Time Agents

Antonio A. Ginart, Naveen Kodali, Jason Lee, Caiming Xiong, Silvio Savarese, John Emmons

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

2408.04870 2024-10-24 cs.CR cs.AI 77%

ConfusedPilot: Confused Deputy Risks in RAG-based LLMs

Ayush RoyChowdhury, Mulong Luo, Prateek Sahu, Sarbartha Banerjee, Mohit Tiwari

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

2410.17267 2024-10-24 cs.CV cs.AI 77%

Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment

Seongjun Jeong, Gi-Cheon Kang, Joochan Kim, Byoung-Tak Zhang

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

2410.16950 2024-10-23 cs.CR cs.AI 77%

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In

Itay Nakash, George Kour, Guy Uziel, Ateret Anaby-Tavor

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

2410.13886 2024-10-23 cs.CR cs.LG 77%

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Scale Red Team, Elaine Chang, Vaughn Robinson, Sean Hendryx, Shuyan Zhou, Matt Fredrikson, Summer Yue, Zifan Wang

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

2402.13521 2024-10-23 cs.SE cs.AI 77%

Test-Driven Development for Code Generation

Noble Saji Mathews, Meiyappan Nagappan

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

2410.13441 2024-10-18 cs.AI cs.SE 77%

Instruction-Driven Game Engine: A Poker Case Study

Hongqiu Wu, Xingyuan Liu, Yan Wang, Hai Zhao

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

Comments EMNLP 2024 Demo. arXiv admin note: substantial text overlap with arXiv:2404.00276

2410.11745 2024-10-16 cs.CL cs.HC 77%

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation

Leon Fröhling, Gianluca Demartini, Dennis Assenmacher

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

Comments 21 pages, 13 figures

2410.09949 2024-10-16 cs.CL 77%

MisinfoEval: Generative AI in the Era of "Alternative Facts"

Saadia Gabriel, Liang Lyu, James Siderius, Marzyeh Ghassemi, Jacob Andreas, Asu Ozdaglar

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

Comments EMNLP 2024. Correspondence can be sent to skgabrie at cs dot ucla dot edu

2410.01953 2024-10-16 cs.CL 77%

Generate then Refine: Data Augmentation for Zero-shot Intent Detection

I-Fan Lin, Faegheh Hasibi, Suzan Verberne

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

2410.09040 2024-10-14 cs.CL 77%

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

Zijun Wang, Haoqin Tu, Jieru Mei, Bingchen Zhao, Yisen Wang, Cihang Xie

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

2410.08922 2024-10-14 cs.HC cs.AI 77%

Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning

Majeed Kazemitabaar, Oliver Huang, Sangho Suh, Austin Z. Henley, Tovi Grossman

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

Comments 19 pages, 6 figures

2410.03857 2024-10-10 cs.CL 77%

You Know What I'm Saying: Jailbreak Attack via Implicit Reference

Tianyu Wu, Lingrui Mei, Ruibin Yuan, Lujun Li, Wei Xue, Yike Guo

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

2402.08874 2024-10-10 cs.CL 77%

Recurrent Alignment with Hard Attention for Hierarchical Text Rating

Chenxi Lin, Jiayu Ren, Guoxiu He, Zhuoren Jiang, Haiyan Yu, Xiaomin Zhu

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

Comments Accepted by EMNLP 2024 Main Conference

2401.04883 2024-10-08 cs.CL 77%

Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations

Manqing Mao, Paishun Ting, Yijian Xiang, Mingyang Xu, Julia Chen, Jianzhe Lin

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

2410.03351 2024-10-07 cs.CL cs.PL cs.SE 77%

Generating Equivalent Representations of Code By A Self-Reflection Approach

Jia Li, Ge Li, Lecheng Wang, Hao Zhu, Zhi Jin

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

2410.02657 2024-10-04 cs.CL cs.CY 77%

Hate Personified: Investigating the role of LLMs in content moderation

Sarah Masud, Sahajpreet Singh, Viktor Hangya, Alexander Fraser, Tanmoy Chakraborty

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

Comments 17 pages, 6 Figures, 13 Tables, EMNLP'24 Mains

2406.12069 2024-10-04 cs.CL 77%

Satyrn: A Platform for Analytics Augmented Generation

Marko Sterbentz, Cameron Barrie, Shubham Shahi, Abhratanu Dutta, Donna Hooshmand, Harper Pack, Kristian J. Hammond

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

Comments Accepted to EMNLP 2024

2309.12934 2024-10-03 cs.CL 77%

TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles

Adaku Uchendu, Thai Le, Dongwon Lee

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

Comments Accepted at The 27th European Conference on Artificial Intelligence (ECAI 2024)

2410.01064 2024-10-03 cs.AI 77%

Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability

Weitong Zhang, Chengqi Zang, Bernhard Kainz

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

2402.17433 2024-09-27 cs.CL 77%

Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder

Jiaqi Wang, Zhenxi Song, Zhengyu Ma, Xipeng Qiu, Min Zhang, Zhiguo Zhang

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

Comments 8 pages (excluding references), accepted by ACL 2024 Main Conference

Journal ref Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Volume 1, pages 7278-7292, August 2024, Bangkok, Thailand

2409.16621 2024-09-26 cs.AI 77%

Entailment-Driven Privacy Policy Classification with LLMs

Bhanuka Silva, Dishanika Denipitiyage, Suranga Seneviratne, Anirban Mahanti, Aruna Seneviratne

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

Comments 8 pages, 4 figures, 3 tables

2409.13702 2024-09-24 cs.CL cs.IR 77%

Shaping the Future of Endangered and Low-Resource Languages -- Our Role in the Age of LLMs: A Keynote at ECIR 2024

Josiane Mothe

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

Journal ref Sigir Forum, 2024, 58 (1), pp.1-13

2409.13676 2024-09-23 cs.SD cs.AI eess.AS 77%

A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification

Michel Olvera, Paraskevas Stamatiadis, Slim Essid

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

Comments DCASE 2024 - 9th Workshop on Detection and Classification of Acoustic Scenes and Events, Oct 2024, Tokyo, Japan

2406.15540 2024-09-19 cs.SE cs.FL cs.LG 77%

Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods

George Granberry, Wolfgang Ahrendt, Moa Johansson

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

2409.11218 2024-09-18 cs.CL 77%

Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis

Lingling Xu, Haoran Xie, S. Joe Qin, Fu Lee Wang, Xiaohui Tao

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

Comments 8 pages, 3 figures

2401.01256 2024-09-17 cs.CV cs.CL 77%

VideoStudio: Generating Consistent-Content and Multi-Scene Videos

Fuchen Long, Zhaofan Qiu, Ting Yao, Tao Mei

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

Comments ECCV 2024. Source code is available at https://github.com/FuchenUSTC/VideoStudio

2404.05047 2024-09-12 cs.LG cs.CR 77%

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4

Bishwas Mandal, George Amariucai, Shuangqing Wei

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

Comments 8 pages, Paper accepted at 2024 IEEE International Joint Conference on Neural Networks (IJCNN)

2408.09236 2024-09-09 cs.IR cs.AI 77%

Hybrid Semantic Search: Unveiling User Intent Beyond Keywords

Aman Ahluwalia, Bishwajit Sutradhar, Karishma Ghosh, Indrapal Yadav, Arpan Sheetal, Prashant Patil

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

1. 其他LLM 12228 篇

Embedding-based classifiers can detect prompt injection attacks

Asynchronous Tool Usage for Real-Time Agents

ConfusedPilot: Confused Deputy Risks in RAG-based LLMs

Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Test-Driven Development for Code Generation

Instruction-Driven Game Engine: A Poker Case Study

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation

MisinfoEval: Generative AI in the Era of "Alternative Facts"

Generate then Refine: Data Augmentation for Zero-shot Intent Detection

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning

You Know What I'm Saying: Jailbreak Attack via Implicit Reference

Recurrent Alignment with Hard Attention for Hierarchical Text Rating

Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations

Generating Equivalent Representations of Code By A Self-Reflection Approach

Hate Personified: Investigating the role of LLMs in content moderation

Satyrn: A Platform for Analytics Augmented Generation

TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles

Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability

Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder

Entailment-Driven Privacy Policy Classification with LLMs

Shaping the Future of Endangered and Low-Resource Languages -- Our Role in the Age of LLMs: A Keynote at ECIR 2024

A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification

Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods

Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis

VideoStudio: Generating Consistent-Content and Multi-Scene Videos

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4

Hybrid Semantic Search: Unveiling User Intent Beyond Keywords