语言大模型 / LLM - arXivDaily 专题

2504.14375 2025-04-22 cs.LG 77%

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts

Kun Qian, Maximillian Chen, Siyan Li, Arpit Sharma, Zhou Yu

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

Comments Accepted by NAACL 2025

2504.14368 2025-04-22 cs.LG cs.CR 77%

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Shlomi Hod, Lucas Rosenblatt, Julia Stoyanovich

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

2411.13055 2025-04-15 cs.LG cs.DC 77%

Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training

Jared Fernandez, Luca Wehrstedt, Leonid Shamis, Mostafa Elhoushi, Kalyan Saladi, Yonatan Bisk, Emma Strubell, Jacob Kahn

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

2504.08112 2025-04-14 cs.LG cond-mat.mtrl-sci 77%

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Chaojian Li, Zhifan Ye, Massimiliano Lupo Pasini, Jong Youl Choi, Cheng Wan, Yingyan Celine Lin, Prasanna Balaprakash

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

Comments Accepted by DAC'25

2504.07964 2025-04-11 cs.LG 77%

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Zhongyang Li, Ziyue Li, Tianyi Zhou

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

2410.15748 2025-04-04 cs.AI 77%

Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation

Shaonan Wu, Shuai Lu, Yeyun Gong, Nan Duan, Ping Wei

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

2404.15458 2025-04-01 physics.optics cs.LG 77%

Learning Electromagnetic Metamaterial Physics With ChatGPT

Darui Lu, Yang Deng, Jordan M. Malof, Willie J. Padilla

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

2411.16781 2025-04-01 cs.CV cs.AI 77%

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Yiheng Li, Ruibing Hou, Hong Chang, Shiguang Shan, Xilin Chen

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

2503.08741 2025-03-27 cs.CV cs.AI 77%

Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis

Letian Zhang, Quan Cui, Bingchen Zhao, Cheng Yang

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

2412.05223 2025-03-27 cs.CL 77%

100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo

Michael C. Wood, Adam A. Forbes

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

2503.18293 2025-03-25 cs.CL 77%

Fact-checking AI-generated news reports: Can LLMs catch their own lies?

Jiayi Yao, Haibo Sun, Nianwen Xue

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

2503.15579 2025-03-21 cs.LG 77%

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

Xingxuan Zhang, Haoran Wang, Jiansheng Li, Yuan Xue, Shikai Guan, Renzhe Xu, Hao Zou, Han Yu, Peng Cui

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

Comments 32 pages

2409.15771 2025-03-20 cs.LG nlin.CD physics.comp-ph 77%

Zero-shot forecasting of chaotic systems

Yuanzhao Zhang, William Gilpin

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

Comments 13th International Conference on Learning Representations (ICLR 2025)

2503.09003 2025-03-13 cs.IR cs.CL 77%

Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs

Mayank Singh, Abhijeet Kumar, Sasidhar Donaparthi, Gayatri Karambelkar

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

Comments Presented in 5th International Conference on NLP & Text Mining (NLTM 2025)

2503.08404 2025-03-12 cs.CL cs.CY 77%

Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information

Elizaveta Kuznetsova, Ilaria Vitulano, Mykola Makhortykh, Martha Stolze, Tomas Nagy, Victoria Vziatysheva

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

Comments 15 pages, 2 figures

2503.07510 2025-03-11 cs.CY cs.CL 77%

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations

Hari Shankar, Vedanta S P, Tejas Cavale, Ponnurangam Kumaraguru, Abhijnan Chakraborty

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

2503.01506 2025-03-04 cs.CL 77%

SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity

Xiangyu Xi, Deyang Kong, Jian Yang, Jiawei Yang, Zhengyu Chen, Wei Wang, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye

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

2502.17239 2025-02-25 cs.CL cs.SD eess.AS 77%

Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction

Tianpeng Li, Jun Liu, Tao Zhang, Yuanbo Fang, Da Pan, Mingrui Wang, Zheng Liang, Zehuan Li, Mingan Lin, Guosheng Dong, Jianhua Xu, Haoze Sun, Zenan Zhou, Weipeng Chen

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

2502.13674 2025-02-20 cs.CL 77%

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari

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

Comments 10 pages, ICLR 2025 conference

2406.12382 2025-02-19 cs.CL 77%

From Instance Training to Instruction Learning: Task Adapters Generation from Instructions

Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Yanchao Hao, Shengping Liu, Kang Liu, Jun Zhao

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 NeurIPS 2024

2502.11460 2025-02-18 cs.CL cs.SE 77%

UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance

Yichuan Ma, Yunfan Shao, Peiji Li, Demin Song, Qipeng Guo, Linyang Li, Xipeng Qiu, Kai Chen

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

Comments work in progress

2410.20163 2025-02-12 cs.IR cs.CL 77%

UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers

Dehai Min, Zhiyang Xu, Guilin Qi, Lifu Huang, Chenyu You

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

Comments NAACL 2025, Main, Long Paper

2402.11633 2025-02-10 cs.CL 77%

Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs

Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, Suzan Verberne

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 at NAACL 2025

2502.03821 2025-02-07 cs.CL 77%

PsyPlay: Personality-Infused Role-Playing Conversational Agents

Tao Yang, Yuhua Zhu, Xiaojun Quan, Cong Liu, Qifan Wang

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

2410.16534 2025-02-06 cs.LG 77%

SoftSRV: Learn to Generate Targeted Synthetic Data

Giulia DeSalvo, Jean-Fracois Kagy, Lazaros Karydas, Afshin Rostamizadeh, Sanjiv Kumar

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

2502.00032 2025-02-04 cs.DB cs.AI cs.IR 77%

Querying Databases with Function Calling

Connor Shorten, Charles Pierse, Thomas Benjamin Smith, Karel D'Oosterlinck, Tuana Celik, Erika Cardenas, Leonie Monigatti, Mohd Shukri Hasan, Edward Schmuhl, Daniel Williams, Aravind Kesiraju, Bob van Luijt

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

Comments Preprint. 23 pages, 7 figures

2502.00022 2025-02-04 cs.AI cs.HC 77%

A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs

Xingyu Xiao, Peng Chen, Qianqian Jia, Jiejuan Tong, Jingang Liang, Haitao Wang

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

2408.09594 2025-02-04 cs.AI 77%

Moonshine: Distilling Game Content Generators into Steerable Generative Models

Yuhe Nie, Michael Middleton, Tim Merino, Nidhushan Kanagaraja, Ashutosh Kumar, Zhan Zhuang, Julian Togelius

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

2501.15915 2025-01-28 cs.CL cs.IR 77%

Parametric Retrieval Augmented Generation

Weihang Su, Yichen Tang, Qingyao Ai, Junxi Yan, Changyue Wang, Hongning Wang, Ziyi Ye, Yujia Zhou, Yiqun Liu

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

2501.11199 2025-01-28 cs.CL 77%

Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation

Ivan Lopez, Fateme Nateghi Haredasht, Kaitlin Caoili, Jonathan H Chen, Akshay Chaudhari

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

1. 预训练与数据 12460 篇

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation

Learning Electromagnetic Metamaterial Physics With ChatGPT

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis

100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo

Fact-checking AI-generated news reports: Can LLMs catch their own lies?

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

Zero-shot forecasting of chaotic systems

Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs

Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations

SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity

Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

From Instance Training to Instruction Learning: Task Adapters Generation from Instructions

UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance

UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers

Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs

PsyPlay: Personality-Infused Role-Playing Conversational Agents

SoftSRV: Learn to Generate Targeted Synthetic Data

Querying Databases with Function Calling

A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs

Moonshine: Distilling Game Content Generators into Steerable Generative Models

Parametric Retrieval Augmented Generation

Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation