语言大模型 / LLM - arXivDaily 专题

2310.08309 2024-03-19 cs.CL 70%

Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning

Zhe Yang, Damai Dai, Peiyi Wang, Zhifang Sui

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

Comments Findings of EMNLP 2023

2403.10408 2024-03-18 cs.CR cs.CY cs.IR cs.LG cs.SI 70%

SocialGenPod: Privacy-Friendly Generative AI Social Web Applications with Decentralised Personal Data Stores

Vidminas Vizgirda, Rui Zhao, Naman Goel

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

Comments Demo paper accepted in Companion Proceedings of the ACM Web Conference 2024

2403.09148 2024-03-15 cs.CL cs.IR 70%

Evaluating LLMs for Gender Disparities in Notable Persons

Lauren Rhue, Sofie Goethals, Arun Sundararajan

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

2403.08426 2024-03-14 cs.CV cs.AI 70%

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation

Zicheng Zhang, Tong Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, QiXiang Ye, Wei Ke

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

2403.08189 2024-03-14 cs.CL 70%

Embedded Translations for Low-resource Automated Glossing

Changbing Yang, Garrett Nicolai, Miikka Silfverberg

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

2201.07381 2024-03-12 cs.AI cs.SE 70%

Unveiling Project-Specific Bias in Neural Code Models

Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Junzhe Jiang, Yang Liu

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

Comments Accepted by LREC-COLING 2024

2403.06039 2024-03-12 cs.HC cs.AI 70%

A Preliminary Exploration of YouTubers' Use of Generative-AI in Content Creation

Yao Lyu, He Zhang, Shuo Niu, Jie Cai

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

Comments Accepted at CHI LBW 2024

2310.19181 2024-03-12 cs.CR cs.CL 70%

From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude

Sayak Saha Roy, Poojitha Thota, Krishna Vamsi Naragam, Shirin Nilizadeh

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

2403.03857 2024-03-08 cs.CL cs.HC 70%

Emojinize: Enriching Any Text with Emoji Translations

Lars Henning Klein, Roland Aydin, Robert West

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

2403.03141 2024-03-06 cs.CL 70%

Language Guided Exploration for RL Agents in Text Environments

Hitesh Golchha, Sahil Yerawar, Dhruvesh Patel, Soham Dan, Keerthiram Murugesan

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

2402.19076 2024-03-01 cs.CL 70%

Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials

Gennaro Nolano, Moritz Blum, Basil Ell, Philipp Cimiano

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

2402.15205 2024-02-26 cs.HC cs.AI 70%

Enhancing ICU Patient Recovery: Using LLMs to Assist Nurses in Diary Writing

Samuel Kernan Freire, Margo MC van Mol, Carola Schol, Elif Özcan Vieira

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

Comments 3 pages, under review

2312.04127 2024-02-26 cs.CL 70%

Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Yanrui Du, Sendong Zhao, Ming Ma, Yuhan Chen, Bing Qin

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

2310.18297 2024-02-23 cs.CV cs.AI 70%

Image Clustering Conditioned on Text Criteria

Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee

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

2310.00297 2024-02-22 cs.CL 70%

Understanding In-Context Learning from Repetitions

Jianhao Yan, Jin Xu, Chiyu Song, Chenming Wu, Yafu Li, Yue Zhang

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

Comments Accepted by ICLR 2024. Updated with new experiments and results

2402.12212 2024-02-20 cs.CL 70%

Polarization of Autonomous Generative AI Agents Under Echo Chambers

Masaya Ohagi

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

2402.11004 2024-02-20 cs.LG 70%

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

Benjamin L. Edelman, Ezra Edelman, Surbhi Goel, Eran Malach, Nikolaos Tsilivis

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

2402.07940 2024-02-14 cs.HC cs.AI cs.CY cs.SI 70%

LLMs Among Us: Generative AI Participating in Digital Discourse

Kristina Radivojevic, Nicholas Clark, Paul Brenner

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

2312.10622 2024-02-14 cs.SE cs.AI 70%

Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Tools

Shreya Bhatia, Tarushi Gandhi, Dhruv Kumar, Pankaj Jalote

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

Comments Accepted to LLM4Code @ ICSE 2024

2310.14174 2024-02-13 cs.CL 70%

An In-Context Schema Understanding Method for Knowledge Base Question Answering

Yantao Liu, Zixuan Li, Xiaolong Jin, Yucan Guo, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

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

2402.04084 2024-02-07 cs.LG cs.DS stat.ML 70%

Provably learning a multi-head attention layer

Sitan Chen, Yuanzhi Li

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

Comments 105 pages, comments welcome

2402.03969 2024-02-07 cs.LG 70%

In-context learning agents are asymmetric belief updaters

Johannes A. Schubert, Akshay K. Jagadish, Marcel Binz, Eric Schulz

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

2402.03901 2024-02-07 cs.IT cs.LG math.IT stat.ML 70%

Batch Universal Prediction

Marco Bondaschi, Michael Gastpar

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

2402.03339 2024-02-07 cs.CL 70%

Interplay of Semantic Communication and Knowledge Learning

Fei Ni, Bingyan Wang, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

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

Comments Contributing to a Wiley book, copyright might be transferred without further notice; And the paper "Knowledge Enhanced Semantic Communication Receiver" (available at arXiv:2302.07727) constitutes a segment of this work

2402.00715 2024-02-06 cs.AI cs.NI stat.ME 70%

Intent Assurance using LLMs guided by Intent Drift

Kristina Dzeparoska, Ali Tizghadam, Alberto Leon-Garcia

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

2401.08711 2024-02-06 cs.HC cs.AI cs.CY 70%

Assistant, Parrot, or Colonizing Loudspeaker? ChatGPT Metaphors for Developing Critical AI Literacies

Anuj Gupta, Yasser Atef, Anna Mills, Maha Bali

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

Comments This is a preprint (accepted version) of an article that has been accepted for publication at the journal Open Praxis: https://openpraxis.org/

2311.14720 2024-01-31 cs.CY cs.AI econ.GN q-fin.EC 70%

Perceptions and Detection of AI Use in Manuscript Preparation for Academic Journals

Nir Chemaya, Daniel Martin

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

2401.15248 2024-01-30 cs.LG stat.ML 70%

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

Yue Xing, Xiaofeng Lin, Qifan Song, Yi Xu, Belinda Zeng, Guang Cheng

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

Comments To appear in AISTATS2024

2308.00319 2024-01-11 cs.CL 70%

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

Hai Zhu, Zhaoqing Yang, Weiwei Shang, Yuren Wu

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

Comments 18 pages, 38th AAAI Main Track

2309.01398 2024-01-03 cs.CL 70%

Zero-shot information extraction from radiological reports using ChatGPT

Danqing Hu, Bing Liu, Xiaofeng Zhu, Xudong Lu, Nan Wu

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

1. 其他LLM 12266 篇

Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning

SocialGenPod: Privacy-Friendly Generative AI Social Web Applications with Decentralised Personal Data Stores

Evaluating LLMs for Gender Disparities in Notable Persons

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation

Embedded Translations for Low-resource Automated Glossing

Unveiling Project-Specific Bias in Neural Code Models

A Preliminary Exploration of YouTubers' Use of Generative-AI in Content Creation

From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude

Emojinize: Enriching Any Text with Emoji Translations

Language Guided Exploration for RL Agents in Text Environments

Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials

Enhancing ICU Patient Recovery: Using LLMs to Assist Nurses in Diary Writing

Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Image Clustering Conditioned on Text Criteria

Understanding In-Context Learning from Repetitions

Polarization of Autonomous Generative AI Agents Under Echo Chambers

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

LLMs Among Us: Generative AI Participating in Digital Discourse

Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Tools

An In-Context Schema Understanding Method for Knowledge Base Question Answering

Provably learning a multi-head attention layer

In-context learning agents are asymmetric belief updaters

Batch Universal Prediction

Interplay of Semantic Communication and Knowledge Learning

Intent Assurance using LLMs guided by Intent Drift

Assistant, Parrot, or Colonizing Loudspeaker? ChatGPT Metaphors for Developing Critical AI Literacies

Perceptions and Detection of AI Use in Manuscript Preparation for Academic Journals

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

Zero-shot information extraction from radiological reports using ChatGPT