语言大模型 / LLM - arXivDaily 专题

2412.16032 2024-12-23 cs.AI cs.LG 62%

A Framework for Streaming Event-Log Prediction in Business Processes

Benedikt Bollig, Matthias Függer, Thomas Nowak

机构 * Université Paris-Saclay（巴黎萨克雷大学）； CNRS（法国国家科学研究中心）； ENS Paris-Saclay（巴黎萨克雷高等师范学校）； Institut Universitaire de France（法国大学研究院）

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

Comments 18 pages

2412.15497 2024-12-23 cs.CL cs.AI 62%

Lexicography Saves Lives (LSL): Automatically Translating Suicide-Related Language

Annika Marie Schoene, John E. Ortega, Rodolfo Joel Zevallos, Laura Haaber Ihle

机构 * Institute for Experiential AI（体验式人工智能研究院）； Barcelona Supercomputing Center（巴塞罗那超级计算中心）

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

Comments The 31st International Conference on Computational Linguistics (COLING 2025)

2412.12433 2024-12-18 cs.CL cs.IR cs.LG 62%

Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models

Chia-Hsuan Chang, Tien-Yuan Huang, Yi-Hang Tsai, Chia-Ming Chang, San-Yih Hwang

机构 * Yale University（耶鲁大学）； National Sun Yat-sen University（国立中山大学）

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

Comments Accepted to 18th BUCC Workshop at COLING 2025

2412.10939 2024-12-17 cs.CY cs.AI cs.CL cs.HC 62%

Human-Centric NLP or AI-Centric Illusion?: A Critical Investigation

Piyapath T Spencer

机构 * Faculty of Arts, CU（朱拉隆功大学文学院）； Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心）

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

Comments Preprint to be published in Proceedings of PACLIC38

2412.06410 2024-12-10 cs.LG cs.AI stat.ML 62%

BatchTopK Sparse Autoencoders

Bart Bussmann, Patrick Leask, Neel Nanda

机构 * Durham University（杜伦大学）

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

2412.00325 2024-12-03 cs.SD cs.AI cs.LG eess.AS 62%

MusicGen-Chord: Advancing Music Generation through Chord Progressions and Interactive Web-UI

Jongmin Jung, Andreas Jansson, Dasaem Jeong

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

Comments Late-breaking/demo (LBD) at ISMIR 2024. https://ismir2024program.ismir.net/lbd_424.html

2411.19140 2024-12-02 cs.CY cs.AI cs.CL cs.HC stat.OT 62%

Examining Multimodal Gender and Content Bias in ChatGPT-4o

Roberto Balestri

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

Comments 17 pages, 4 figures, 3 tables. Conference: "14th International Conference on Artificial Intelligence, Soft Computing and Applications (AIAA 2024), London, 23-24 November 2024" It will be published in the proceedings "David C. Wyld et al. (Eds): IoTE, CNDC, DSA, AIAA, NLPTA, DPPR - 2024"

2410.04683 2024-11-25 cs.LG cs.AI 62%

Towards Measuring Goal-Directedness in AI Systems

Dylan Xu, Juan-Pablo Rivera

机构 * University of California, Berkeley（加利福尼亚大学伯克利分校）； Georgia Tech University（佐治亚理工学院）

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

Comments Updated acknowledgements

2411.13453 2024-11-21 cs.CL cs.AI 62%

LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models

Salvatore Mario Carta, Stefano Chessa, Giulia Contu, Andrea Corriga, Andrea Deidda, Gianni Fenu, Luca Frigau, Alessandro Giuliani, Luca Grassi, Marco Manolo Manca, Mirko Marras, Francesco Mola, Bastianino Mossa, Piergiorgio Mura, Marco Ortu, Leonardo Piano, Simone Pisano, Alessia Pisu, Alessandro Sebastian Podda, Livio Pompianu, Simone Seu, Sandro Gabriele Tiddia

机构 * University of Cagliari（卡利亚里大学）； VisioScientiae S.r.l.（VisioScientiae有限公司）； The Cloud Alchemist S.r.l.（Cloud Alchemist有限公司）； University for Foreigners of Siena（锡耶纳外国人大学）

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

2401.12202 2024-11-20 cs.RO cs.AI cs.CV cs.LG 62%

OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics

Peiqi Liu, Yaswanth Orru, Jay Vakil, Chris Paxton, Nur Muhammad Mahi Shafiullah, Lerrel Pinto

机构 * New York University（纽约大学）； Meta

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

Comments Github repo: https://github.com/ok-robot/ok-robot

2411.05277 2024-11-11 cs.CR cs.CL cs.LG 62%

Revisiting the Robustness of Watermarking to Paraphrasing Attacks

Saksham Rastogi, Danish Pruthi

机构 * Indian Institute of Science（印度科学学院）

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

Comments EMNLP 2024

2411.00680 2024-11-04 cs.CL cs.LG stat.ML 62%

Zipfian Whitening

Sho Yokoi, Han Bao, Hiroto Kurita, Hidetoshi Shimodaira

机构 * Tohoku University（东北大学）； RIKEN（理化学研究所）； Kyoto University（京都大学）

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

Comments NeurIPS 2024

2410.23483 2024-11-01 cs.LG cs.AI cs.CR cs.CV cs.MA 62%

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System

Julian Collado, Kevin Stangl

机构 * HiddenLayer Inc.（隐层公司）

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

Comments 11 pages, 2 figures

2410.22285 2024-10-30 cs.CL cs.AI 62%

From melodic note sequences to pitches using word2vec

Daniel Defays

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

Comments 12 pages, 6 figures

2312.01276 2024-10-30 cs.AI cs.CL 62%

Toward best research practices in AI Psychology

Anna A. Ivanova

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

2410.18100 2024-10-25 cs.CV cs.AI cs.CL 62%

RingGesture: A Ring-Based Mid-Air Gesture Typing System Powered by a Deep-Learning Word Prediction Framework

Junxiao Shen, Roger Boldu, Arpit Kalla, Michael Glueck, Hemant Bhaskar Surale Amy Karlson

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

2404.01335 2024-10-24 cs.LG cs.AI 62%

Generative AI Models for Different Steps in Architectural Design: A Literature Review

Chengyuan Li, Tianyu Zhang, Xusheng Du, Ye Zhang, Haoran Xie

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

Comments 34 pages, 14 figures, accepted by Frontiers of Architectural Research

2402.08777 2024-10-23 q-bio.GN cs.AI cs.CE cs.CL 62%

DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings

Zhihan Zhou, Weimin Wu, Harrison Ho, Jiayi Wang, Lizhen Shi, Ramana V Davuluri, Zhong Wang, Han Liu

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

2410.15578 2024-10-22 cs.LG cs.CL 62%

Generalized Probabilistic Attention Mechanism in Transformers

DongNyeong Heo, Heeyoul Choi

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

2410.13111 2024-10-18 cs.LG cs.CL stat.ML 62%

Controllable Generation via Locally Constrained Resampling

Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck

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

Comments arXiv admin note: text overlap with arXiv:2312.03905

2410.08469 2024-10-17 cs.LG cs.CL cs.CV 62%

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Eunji Kim, Kyuhong Shim, Simyung Chang, Sungroh Yoon

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

Comments Accepted at EMNLP 2024 Findings

2408.09111 2024-10-16 cs.AI cs.CL cs.CV cs.HC 62%

Measuring Agreeableness Bias in Multimodal Models

Jaehyuk Lim, Bruce W. Lee

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

2410.09350 2024-10-15 cs.CL cs.AI 62%

Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation

Jinyoung Park, Minseok Joo, Joo-Kyung Kim, Hyunwoo J. Kim

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

Comments EMNLP (main)

2406.19874 2024-10-10 cs.CL cs.AI 62%

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood

Yang Xu, Yu Wang, Hao An, Zhichen Liu, Yongyuan Li

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

Comments 14 pages, 12 figures

2403.15837 2024-10-10 cs.CV cs.CL cs.LG 62%

Centered Masking for Language-Image Pre-Training

Mingliang Liang, Martha Larson

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

2410.03470 2024-10-07 cs.LG cs.AI math.AT 62%

Vulnerability Detection via Topological Analysis of Attention Maps

Pavel Snopov, Andrey Nikolaevich Golubinskiy

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

Comments Accepted to ITaS2024. Contains 8 pages

2410.00134 2024-10-04 cs.CL cs.AI 62%

Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms

Melkamu Abay Mersha, Mesay Gemeda yigezu, Jugal Kalita

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

Journal ref ACLing2024 6th International Conference on AI in Computational Linguistics

2410.01649 2024-10-03 cs.LG cs.AI 62%

shapiq: Shapley Interactions for Machine Learning

Maximilian Muschalik, Hubert Baniecki, Fabian Fumagalli, Patrick Kolpaczki, Barbara Hammer, Eyke Hüllermeier

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

Comments NeurIPS 2024

2308.12108 2024-10-02 stat.ML cs.AI cs.LG 62%

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

Edmund Lau, Zach Furman, George Wang, Daniel Murfet, Susan Wei

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

Comments This version contains new empirical results and merged content from a related paper (arXiv:2402.03698) to provide a more comprehensive study

2404.09577 2024-09-27 cs.CL cs.AI 62%

Transformers, Contextualism, and Polysemy

Jumbly Grindrod

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

1. 其他LLM 12287 篇

A Framework for Streaming Event-Log Prediction in Business Processes

Lexicography Saves Lives (LSL): Automatically Translating Suicide-Related Language

Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models

Human-Centric NLP or AI-Centric Illusion?: A Critical Investigation

BatchTopK Sparse Autoencoders

MusicGen-Chord: Advancing Music Generation through Chord Progressions and Interactive Web-UI

Examining Multimodal Gender and Content Bias in ChatGPT-4o

Towards Measuring Goal-Directedness in AI Systems

LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models

OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics

Revisiting the Robustness of Watermarking to Paraphrasing Attacks

Zipfian Whitening

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System

From melodic note sequences to pitches using word2vec

Toward best research practices in AI Psychology

RingGesture: A Ring-Based Mid-Air Gesture Typing System Powered by a Deep-Learning Word Prediction Framework

Generative AI Models for Different Steps in Architectural Design: A Literature Review

DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings

Generalized Probabilistic Attention Mechanism in Transformers

Controllable Generation via Locally Constrained Resampling

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Measuring Agreeableness Bias in Multimodal Models

Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood

Centered Masking for Language-Image Pre-Training

Vulnerability Detection via Topological Analysis of Attention Maps

Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms

shapiq: Shapley Interactions for Machine Learning

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

Transformers, Contextualism, and Polysemy