语言大模型 / LLM - arXivDaily 专题

2408.12186 2024-10-03 stat.ML cs.LG 77%

Transformers are Minimax Optimal Nonparametric In-Context Learners

Juno Kim, Tai Nakamaki, Taiji Suzuki

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

Comments NeurIPS 2024; 40 pages, 3 figures

2308.09895 2024-09-24 cs.PL cs.LG 77%

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs

Federico Cassano, John Gouwar, Francesca Lucchetti, Claire Schlesinger, Anders Freeman, Carolyn Jane Anderson, Molly Q Feldman, Michael Greenberg, Abhinav Jangda, Arjun Guha

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

2404.11568 2024-09-12 cs.LG 77%

On the Scalability of GNNs for Molecular Graphs

Maciej Sypetkowski, Frederik Wenkel, Farimah Poursafaei, Nia Dickson, Karush Suri, Philip Fradkin, Dominique Beaini

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

2408.14972 2024-08-28 cs.CL 77%

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

Chi-Min Chan, Jianxuan Yu, Weize Chen, Chunyang Jiang, Xinyu Liu, Weijie Shi, Zhiyuan Liu, Wei Xue, Yike Guo

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

2310.08750 2024-08-26 cs.LG 77%

Search-Adaptor: Embedding Customization for Information Retrieval

Jinsung Yoon, Sercan O Arik, Yanfei Chen, Tomas Pfister

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

Comments Published in 2024 ACL Main Conference

2408.05793 2024-08-13 cs.CL 77%

SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events

Sai Vallurupalli, Katrin Erk, Francis Ferraro

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

Comments Accepted to Findings of the Association for Computational Linguistics 2024

2408.03256 2024-08-07 cs.CL 77%

Synthesizing Text-to-SQL Data from Weak and Strong LLMs

Jiaxi Yang, Binyuan Hui, Min Yang, Jian Yang, Junyang Lin, Chang Zhou

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

Comments 12 pages, 7 figures, ACL 2024

2406.07867 2024-08-05 cs.CV cs.AI cs.HC 77%

Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

Se Jin Park, Chae Won Kim, Hyeongseop Rha, Minsu Kim, Joanna Hong, Jeong Hun Yeo, Yong Man Ro

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

Comments Accepted to ACL 2024 (Oral)

2402.18819 2024-08-05 cs.LG 77%

Dual Operating Modes of In-Context Learning

Ziqian Lin, Kangwook Lee

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

Comments 54 pages, 23 figures

2407.08699 2024-07-17 cs.LG 77%

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang, Martin Vechev, Kristina Toutanova

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

2403.15042 2024-07-16 cs.CL 77%

LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

Nicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam, Sheng Shen, Gopala Anumanchipalli, Michael W. Mahoney, Kurt Keutzer, Amir Gholami

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

Comments ACL 2024

2407.00497 2024-07-02 cs.CL 77%

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement

Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan

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

2406.12570 2024-06-19 cs.CL 77%

Applying Ensemble Methods to Model-Agnostic Machine-Generated Text Detection

Ivan Ong, Boon King Quek

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

2402.10738 2024-06-18 cs.CL 77%

Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning

Yinpeng Liu, Jiawei Liu, Xiang Shi, Qikai Cheng, Yong Huang, Wei Lu

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

2401.02906 2024-06-18 cs.CR cs.CL cs.CV 77%

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang

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

2406.09462 2024-06-17 cs.CV cs.AI 77%

SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Video

Hector A. Valdez, Kyle Min, Subarna Tripathi

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

2401.10186 2024-06-07 cs.CL 77%

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

Zdeněk Kasner, Ondřej Dušek

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

Comments Accepted to ACL 2024 Main Conference

2402.09989 2024-05-30 cs.CV cs.CL 77%

LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition

Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, Gang Pan

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

Comments Accepted to Findings of ACL 2024

2405.07703 2024-05-20 cs.CL 77%

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs

Mihai Masala, Denis C. Ilie-Ablachim, Dragos Corlatescu, Miruna Zavelca, Marius Leordeanu, Horia Velicu, Marius Popescu, Mihai Dascalu, Traian Rebedea

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

2405.08120 2024-05-15 cs.ET cs.AI 77%

From Questions to Insightful Answers: Building an Informed Chatbot for University Resources

Subash Neupane, Elias Hossain, Jason Keith, Himanshu Tripathi, Farbod Ghiasi, Noorbakhsh Amiri Golilarz, Amin Amirlatifi, Sudip Mittal, Shahram Rahimi

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

2404.19146 2024-05-01 cs.AI cs.IR 77%

Automated Construction of Theme-specific Knowledge Graphs

Linyi Ding, Sizhe Zhou, Jinfeng Xiao, Jiawei Han

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

2404.14361 2024-04-30 cs.CL 77%

Better Synthetic Data by Retrieving and Transforming Existing Datasets

Saumya Gandhi, Ritu Gala, Vijay Viswanathan, Tongshuang Wu, Graham Neubig

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

Comments PDF fixed in v3

2312.11713 2024-04-26 cs.RO cs.AI 77%

Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies

Jared Strader, Nathan Hughes, William Chen, Alberto Speranzon, Luca Carlone

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

Comments 10 pages, 6 figures, accepted to Robotics and Automation Letters

2404.00152 2024-04-24 cs.CL 77%

On-the-fly Definition Augmentation of LLMs for Biomedical NER

Monica Munnangi, Sergey Feldman, Byron C Wallace, Silvio Amir, Tom Hope, Aakanksha Naik

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

Comments To appear at NAACL 2024 (Main)

2311.14530 2024-04-16 cs.CL 77%

Machine Translation for Ge'ez Language

Aman Kassahun Wassie

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

Comments 8 pages, 1 figure

2310.10118 2024-04-09 cs.CL 77%

Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset

Arthur Amalvy, Vincent Labatut, Richard Dufour

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

Journal ref Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, Dec 2023, Singapore, Singapore. pp.10372-10382

2311.03301 2024-04-05 cs.CL 77%

Ziya2: Data-centric Learning is All LLMs Need

Ruyi Gan, Ziwei Wu, Renliang Sun, Junyu Lu, Xiaojun Wu, Dixiang Zhang, Kunhao Pan, Junqing He, Yuanhe Tian, Ping Yang, Qi Yang, Hao Wang, Jiaxing Zhang, Yan Song

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

2404.02755 2024-04-04 cs.CV cs.AI cs.MM 77%

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

Hao Wu, Huabin Liu, Yu Qiao, Xiao Sun

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

Comments Accepted by CVPR 2024

2404.00610 2024-04-02 cs.CL 77%

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, Jie Fu

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

2404.00303 2024-04-02 cs.CL 77%

A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs

Md Saroar Jahan, Mourad Oussalah, Djamila Romaissa Beddia, Jhuma kabir Mim, Nabil Arhab

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

Comments 31 page, Table 18, Figure 14

1. 预训练与数据 12460 篇

Transformers are Minimax Optimal Nonparametric In-Context Learners

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs

On the Scalability of GNNs for Molecular Graphs

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

Search-Adaptor: Embedding Customization for Information Retrieval

SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events

Synthesizing Text-to-SQL Data from Weak and Strong LLMs

Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

Dual Operating Modes of In-Context Learning

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement

Applying Ensemble Methods to Model-Agnostic Machine-Generated Text Detection

Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Video

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs

From Questions to Insightful Answers: Building an Informed Chatbot for University Resources

Automated Construction of Theme-specific Knowledge Graphs

Better Synthetic Data by Retrieving and Transforming Existing Datasets

Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies

On-the-fly Definition Augmentation of LLMs for Biomedical NER

Machine Translation for Ge'ez Language

Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset

Ziya2: Data-centric Learning is All LLMs Need

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs