语言大模型 / LLM - arXivDaily 专题

2406.13698 2024-11-11 cs.CL 70%

MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language

Shun Wang, Ge Zhang, Han Wu, Tyler Loakman, Wenhao Huang, Chenghua Lin

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2404.06393 2024-11-06 cs.SD cs.AI eess.AS 70%

MuPT: A Generative Symbolic Music Pretrained Transformer

Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, Xinrun Du, Shuyue Guo, Yiming Liang, Yizhi Li, Shangda Wu, Junting Zhou, Tianyu Zheng, Ziyang Ma, Fengze Han, Wei Xue, Gus Xia, Emmanouil Benetos, Xiang Yue, Chenghua Lin, Xu Tan, Stephen W. Huang, Jie Fu, Ge Zhang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

2406.18776 2024-11-05 cs.CL 70%

Implicit Discourse Relation Classification For Nigerian Pidgin

Muhammed Saeed, Peter Bourgonje, Vera Demberg

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2406.10209 2024-11-05 cs.CL 70%

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Abhimanyu Hans, Yuxin Wen, Neel Jain, John Kirchenbauer, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, Jonas Geiping, Abhinav Bhatele, Tom Goldstein

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 10 pages, 8 figures, and 1 table in the main body. Code available at https://github.com/ahans30/goldfish-loss and checkpoints at https://huggingface.co/collections/tomg-group-umd/goldfish-loss-mitigating-memorization-in-llms-66c175becb6aab07744f7272

2410.23514 2024-11-01 cs.CL 70%

Neural spell-checker: Beyond words with synthetic data generation

Matej Klemen, Martin Božič, Špela Arhar Holdt, Marko Robnik-Šikonja

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Camera-ready version. Accepted to TSD 2024

2410.22570 2024-10-31 cond-mat.mtrl-sci cs.LG 70%

Orb: A Fast, Scalable Neural Network Potential

Mark Neumann, James Gin, Benjamin Rhodes, Steven Bennett, Zhiyi Li, Hitarth Choubisa, Arthur Hussey, Jonathan Godwin

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)；分类 cs.LG

2410.22143 2024-10-30 cs.CL 70%

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Vishal Kumar, Zeyi Liao, Jaylen Jones, Huan Sun

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2410.21254 2024-10-29 cs.CL 70%

Are BabyLMs Second Language Learners?

Lukas Edman, Lisa Bylinina, Faeze Ghorbanpour, Alexander Fraser

专题命中预训练与数据：LLM(abstract)；pretraining(abstract)；分类 cs.CL

2410.20838 2024-10-29 cs.CL 70%

A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction

Nankai Lin, Meiyu Zeng, Wentao Huang, Shengyi Jiang, Lixian Xiao, Aimin Yang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2410.18605 2024-10-25 cs.LG 70%

Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study

Tianze Wang, Maryam Honari-Jahromi, Styliani Katsarou, Olga Mikheeva, Theodoros Panagiotakopoulos, Oleg Smirnov, Lele Cao, Sahar Asadi

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.LG

Comments published in Workshop on Customizable NLP at EMNLP 2024

2410.17670 2024-10-24 cs.CL 70%

Quantifying the Risks of Tool-assisted Rephrasing to Linguistic Diversity

Mengying Wang, Andreas Spitz

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2407.11417 2024-10-22 cs.CL 70%

SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

Shicheng Liu, Sina J. Semnani, Harold Triedman, Jialiang Xu, Isaac Dan Zhao, Monica S. Lam

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Findings of EMNLP 2024

2410.14028 2024-10-21 cs.CL 70%

Measuring and Modifying the Readability of English Texts with GPT-4

Sean Trott, Pamela D. Rivière

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 9 pages, 6 figures, workshop TSAR 2024

2410.13667 2024-10-18 cs.CL 70%

ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization

Xiutian Zhao, Ke Wang, Wei Peng

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments In EMNLP 2023

2409.12182 2024-10-18 cs.AI cond-mat.mtrl-sci cond-mat.stat-mech math.DS 70%

LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata

Jaime A. Berkovich, Markus J. Buehler

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

2410.12766 2024-10-17 cs.LG 70%

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

Ekansh Sharma, Daniel M. Roy, Gintare Karolina Dziugaite

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)；分类 cs.LG

2407.13300 2024-10-17 cs.CL eess.AS 70%

Robust ASR Error Correction with Conservative Data Filtering

Takuma Udagawa, Masayuki Suzuki, Masayasu Muraoka, Gakuto Kurata

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2024 Industry Track

2410.11820 2024-10-16 cs.LG 70%

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

Yiding Jiang, Allan Zhou, Zhili Feng, Sadhika Malladi, J. Zico Kolter

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)；分类 cs.LG

Comments 21 pages, 10 figures

2410.10576 2024-10-15 cs.CL 70%

Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?

Zeno Vandenbulcke, Lukas Vermeire, Miryam de Lhoneux

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments To appear at the 4th Multilingual NLP workshop collocated with EMNLP 2024

2410.09347 2024-10-15 cs.CV cs.LG eess.IV 70%

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Huayu Chen, Hang Su, Peize Sun, Jun Zhu

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.LG

2410.09168 2024-10-15 cs.CL 70%

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications

Alexey Zhezherau, Alexei Yanockin

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 22 pages, 7 figures

2410.04279 2024-10-15 cs.LG stat.ML 70%

Black Boxes and Looking Glasses: Multilevel Symmetries, Reflection Planes, and Convex Optimization in Deep Networks

Emi Zeger, Mert Pilanci

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.LG

2403.18593 2024-10-15 cs.CV cs.AI 70%

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding

Run Shao, Zhaoyang Zhang, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 24 pages, 9 figures, 8 tables

Journal ref ISPRS Journal of Photogrammetry and Remote Sensing 2024

2410.04840 2024-10-10 cs.LG stat.ML 70%

Strong Model Collapse

Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.LG

2403.04701 2024-10-10 cs.CV cs.AI 70%

ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes

Hashmat Shadab Malik, Muhammad Huzaifa, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

Journal ref Asian Conference on Computer Vision - 2024

2407.01264 2024-10-08 cs.CL 70%

SignCLIP: Connecting Text and Sign Language by Contrastive Learning

Zifan Jiang, Gerard Sant, Amit Moryossef, Mathias Müller, Rico Sennrich, Sarah Ebling

专题命中预训练与数据：pretraining(abstract)；prompting(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2024 (Main)

2406.13444 2024-10-07 cs.CL cs.CV 70%

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs

Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments EMNLP 2024 Findings

2409.19523 2024-10-01 cs.CL 70%

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation

Shaolin Zhu, Leiyu Pan, Bo Li, Deyi Xiong

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2409.16807 2024-09-26 cs.CL 70%

A Few Hypocrites: Few-Shot Learning and Subtype Definitions for Detecting Hypocrisy Accusations in Online Climate Change Debates

Paulina Garcia Corral, Avishai Green, Hendrik Meyer, Anke Stoll, Xiaoyue Yan, Myrthe Reuver

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments cite the public version, published at CPSS 2024 @ KONVENS

2409.13496 2024-09-23 cs.CV cs.AI 70%

DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring

Ling Wang, Chen Wu, Lin Wang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.AI

1. 预训练与数据 12486 篇

MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language

MuPT: A Generative Symbolic Music Pretrained Transformer

Implicit Discourse Relation Classification For Nigerian Pidgin

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Neural spell-checker: Beyond words with synthetic data generation

Orb: A Fast, Scalable Neural Network Potential

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Are BabyLMs Second Language Learners?

A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction

Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study

Quantifying the Risks of Tool-assisted Rephrasing to Linguistic Diversity

SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

Measuring and Modifying the Readability of English Texts with GPT-4

ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization

LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

Robust ASR Error Correction with Conservative Data Filtering

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications

Black Boxes and Looking Glasses: Multilevel Symmetries, Reflection Planes, and Convex Optimization in Deep Networks

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding

Strong Model Collapse

ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes

SignCLIP: Connecting Text and Sign Language by Contrastive Learning

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation

A Few Hypocrites: Few-Shot Learning and Subtype Definitions for Detecting Hypocrisy Accusations in Online Climate Change Debates

DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring