arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 12597 信号源:cs.CL, cs.AI, cs.LG

1. 领域大模型 12597 篇

2408.01346 2024-08-05 cs.CY cs.CL physics.soc-ph 81%

Prompt Refinement or Fine-tuning? Best Practices for using LLMs in Computational Social Science Tasks

Anders Giovanni Møller, Luca Maria Aiello

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 5 pages, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.19584 2024-07-30 cs.CL 81%

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Pierre Colombo, Telmo Pires, Malik Boudiaf, Rui Melo, Dominic Culver, Sofia Morgado, Etienne Malaboeuf, Gabriel Hautreux, Johanne Charpentier, Michael Desa

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);pretraining(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.07376 2024-07-12 cs.CL 81%

LLMs in Biomedicine: A study on clinical Named Entity Recognition

Masoud Monajatipoor, Jiaxin Yang, Joel Stremmel, Melika Emami, Fazlolah Mohaghegh, Mozhdeh Rouhsedaghat, Kai-Wei Chang

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.17977 2024-07-09 cs.AI cs.MA 81%

Advancing Healthcare Automation: Multi-Agent System for Medical Necessity Justification

Himanshu Pandey, Akhil Amod, Shivang

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments Accepted at BioNLP2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.08066 2024-04-15 cs.CL 81%

MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference

Mobashir Sadat, Cornelia Caragea

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments Accepted to the NAACL 2024 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.00176 2024-04-08 cs.CL 81%

ChipNeMo: Domain-Adapted LLMs for Chip Design

Mingjie Liu, Teodor-Dumitru Ene, Robert Kirby, Chris Cheng, Nathaniel Pinckney, Rongjian Liang, Jonah Alben, Himyanshu Anand, Sanmitra Banerjee, Ismet Bayraktaroglu, Bonita Bhaskaran, Bryan Catanzaro, Arjun Chaudhuri, Sharon Clay, Bill Dally, Laura Dang, Parikshit Deshpande, Siddhanth Dhodhi, Sameer Halepete, Eric Hill, Jiashang Hu, Sumit Jain, Ankit Jindal, Brucek Khailany, George Kokai, Kishor Kunal, Xiaowei Li, Charley Lind, Hao Liu, Stuart Oberman, Sujeet Omar, Ghasem Pasandi, Sreedhar Pratty, Jonathan Raiman, Ambar Sarkar, Zhengjiang Shao, Hanfei Sun, Pratik P Suthar, Varun Tej, Walker Turner, Kaizhe Xu, Haoxing Ren

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);pretraining(abstract)

Comments Updated results for ChipNeMo-70B model

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.11278 2024-03-27 cs.CL 81%

Generator-Retriever-Generator Approach for Open-Domain Question Answering

Abdelrahman Abdallah, Adam Jatowt

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.07822 2024-02-14 cs.CL 81%

CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration

Rachneet Sachdeva, Martin Tutek, Iryna Gurevych

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);small language model(abstract)

Comments Accepted to EACL 2024 main conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.13274 2024-01-22 cs.CL 81%

Enhancing Summarization Performance through Transformer-Based Prompt Engineering in Automated Medical Reporting

Daphne van Zandvoort, Laura Wiersema, Tom Huibers, Sandra van Dulmen, Sjaak Brinkkemper

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 12 pages, 4 figures, to be presented at HEALTHINF 2024, author contributions: research conducted and written by Daphne van Zandvoort and Laura Wiersema, research suggested and used software created by Tom Huibers, data provided and feedback provided by Sandra van Dulmen, supervision and feedback provided by Sjaak Brinkkemper

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.12006 2023-12-20 cs.CL cs.SI 81%

Can ChatGPT be Your Personal Medical Assistant?

Md. Rafiul Biswas, Ashhadul Islam, Zubair Shah, Wajdi Zaghouani, Samir Brahim Belhaouari

专题命中 领域大模型 :large language model(abstract,comments);language model(abstract,comments);LLM(abstract);分类 cs.CL

Comments 5 pages, 7 figures, two tables, Accepted on The International Symposium on Foundation and Large Language Models (FLLM2023)

Journal ref The International Symposium on Foundation and Large Language Models (FLLM2023) https://fllm-conference.org/2023/

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.04494 2023-12-08 cs.HC cs.AI cs.CV cs.GR 81%

AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making

Shusen Liu, Haichao Miao, Zhimin Li, Matthew Olson, Valerio Pascucci, Peer-Timo Bremer

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);foundation model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.07457 2023-07-14 cs.CL 81%

Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation

Tu Anh Dinh, Jan Niehues

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments Accepted to MT Summit 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.07605 2023-05-23 cs.CY cs.AI 81%

Generative AI: Implications and Applications for Education

Anastasia Olga, Tzirides, Akash Saini, Gabriela Zapata, Duane Searsmith, Bill Cope, Mary Kalantzis, Vania Castro, Theodora Kourkoulou, John Jones, Rodrigo Abrantes da Silva, Jen Whiting, Nikoleta Polyxeni Kastania

专题命中 领域大模型 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 34 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.19181 2026-07-22 cs.CL cs.AI cs.LG 新提交 81%

Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning

翻译前推理:用结构化推理增强法律机器翻译

Aixiu An, Michael Jungo, Eloi Eynard, Mark Drenhaus, Andreas Fischer, Jean Hennebert, Sébastien Rumley

专题命中 领域大模型 :SFT(abstract,comments);language model(abstract);small language model(abstract);分类 cs.CL、cs.AI、cs.LG

AI总结 研究法律领域神经机器翻译难题,通过比较多种方法,评估小型语言模型在不同再训练范式下的表现,以瑞士法律系统为测试平台,发现强化学习效果好,增强小型模型接近前沿推理模型,再训练范式随模型规模收益递减。

Comments Code available at https://github.com/aixiuxiuxiu/Legal-MT-SFT-RL

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06089 2026-06-05 q-fin.MF econ.GN q-fin.EC q-fin.RM 81%

Leveraging LLMs for Unstructured Claims Data Analysis

利用大语言模型进行非结构化索赔数据分析

Robert D. Lieberthal, Richard Tran, Vietbao Phan, Jawand Singh, Elizabeth Sottung

专题命中 领域大模型 :LLM(abstract,abstract_cn);large language model(abstract);language model(abstract)

AI总结 提出一个两阶段处理框架,利用大语言模型从非结构化索赔数据中提取结构化精算变量,并通过链梯法准备金验证其实际价值。

Comments 41 pages, 6 figures, 3 tables. Code available at https://github.com/mdsight/llm-claims-analysis . Technical Specification Requirement included as Appendix D. Funded by the Casualty Actuarial Society Artificial Intelligence Working Group

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.18116 2026-08-20 cs.CL cs.LG 新提交 81%

You Are What You Prompt: Prompt Quality, Domain Shift, and Uncertainty in Agrifood Vision-Language Models

你即你所提示的:农业食品视觉语言模型中的提示质量、领域偏移与不确定性

Andrea Morales-Garzón, Salvador López-Joya, Miguel López-Pérez, Maria J. Martin-Bautista

机构 * University of Granada(格拉纳达大学)

专题命中 领域大模型 :language model(title,abstract);分类 cs.CL、cs.LG

AI总结 该研究针对农业食品领域,评估了零样本提示集成(ZPE)在分布内与分布外场景的表现,提出PID方法提升严重领域偏移下的故障检测能力,验证了领域特定提示池的优势。

Comments Accepted in the journal Procesamiento del Lenguaje Natural (SEPLN2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.18086 2026-08-20 cs.AI cs.LG 新提交 81%

Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models

立场:当前模型卡片不足以支持开放权重基础模型的下游治理

Sungwon Chae, Keonwoo Kim, Hoki Kim, Jaeyeon Ju, Sangchul Park

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 本文分析Hugging Face的500份模型卡片,指出现有模型卡片无法支持开放权重基础模型下游治理,提出需整合模型卡片、可接受使用政策、许可证的多层治理框架。

Comments Accepted as a position paper at ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08825 2026-08-11 cs.LG cs.AI q-fin.ST 新提交 81%

Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction

用于冻结时间序列基础模型的混合神经-经典校正:高频股票预测的全面消融研究

Kasun Dewage, Suranadi De Silva, Shankhadeep Mondal

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 本研究针对高频股票预测任务,对冻结的TimesFM模型开展混合神经-经典校正的全面消融实验,发现经典残差学习贡献最大,GatedLinear+RF性能最优,为基础模型适配提供了实用指导。

Comments Accepted and presented at IJCNN 2026, part of the IEEE World Congress on Computational Intelligence (WCCI 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07705 2026-08-11 cs.AI cs.LG 新提交 81%

Protecting patient privacy in clinical foundation models: Technical and legal perspectives

临床基础模型中的患者隐私保护:技术与法律视角

Sana Tonekaboni, Lena Stempfle, Sasha Ronaghi, Corinna Coupette, I. Glenn Cohen, Emily Alsentzer, Marzyeh Ghassemi

机构 * Massachusetts Institute of Technology (MIT)(麻省理工学院(MIT)) The Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所) Borealis AI Stanford University(斯坦福大学) Aalto University(阿尔托大学) Max Planck Institute for Tax Law and Public Finance(马克斯·普朗克税法与公共财政研究所) Stanford Law School(斯坦福法学院) Harvard Law School(哈佛法学院) Petrie-Flom Center for Health Law Policy, Biotechnology & Bioethics(皮里-弗洛姆健康法律政策、生物技术与生物伦理中心)

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 针对临床基础模型的隐私风险,提出实用评估框架,结合技术与法律措施缓解泄露,在保留模型价值的同时保护患者隐私。

Comments 14 pages, 2 Figures, 2 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.16235 2026-08-11 cs.LG cs.AI 版本更新 81%

OpenMHC: Accelerating the Science of Wearable Foundation Models

OpenMHC:加速可穿戴基础模型科学发展

Narayan Schuetz, Yuze Bai, Lianggang Pan, Edgar Eggert, Favour Nerrise, Juan Delgado-SanMartin, Max Rosenblattl, Milana Gurbanova, Mohammad Asadi, Anders Johnson, Paul Schmiedmayer, Dennis Wang, Allan Lawrie, Daniel Seung Kim, Xin Liu, Akshay Paruchuri, Ehsan Adeli, Euan Ashley, Kelly W. Zhang

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 为加速可穿戴健康领域开放科学,发布OpenMHC这一最大最全的可穿戴健康数据集及模型开源实现,引入统一开放基准,对多种模型进行测试,通过大规模开源数据、代码和模型权重,推动可穿戴健康AI研究发展。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.06409 2026-08-10 cs.CL cs.AI 新提交 81%

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models

区分语音语言模型中的决策规则失配与读出覆盖限制

Linkai Peng, Baorian Nuchged

机构 * Institute for the Brain and Cognitive Sciences, University of Connecticut(康涅狄格大学脑与认知科学研究所) Department of Linguistics, The University of Texas at Austin(德克萨斯大学奥斯汀分校语言学系)

专题命中 领域大模型 :language model(title,abstract);分类 cs.CL、cs.AI

AI总结 该研究提出生成对齐诊断阶梯,区分语音语言模型的决策规则失配与读出覆盖限制,发现状态解码比生成准确率高27.8点,无标签logit校正可提升生成准确率,明确性能损失来源。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.26533 2026-07-30 cs.LG cs.AI 新提交 81%

AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control

AgentGFM:具备节点智能体信息流控制的图基础模型

Jingbo Cui, Jitao Zhao, Di Jin, Dongxiao He

机构 * School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院)

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 针对现有图基础模型固定传播方案不适配节点多样结构模式的问题,提出AgentGFM,以节点为智能体通过预测-行动-观察-修正实现自适应信息流控制,实验验证其在多样图拓扑中的有效性。

Comments 13 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.02632 2026-07-28 cs.LG cs.AI 版本更新 81%

QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting

QuantFlow:一种基于联合曼巴的用于时间序列预测的后Transformer基础模型

Shah Nawaz Haider, Steve Austin, Arnab Barua, Sarowar Morshed Shawon, Hadaate Ullah

机构 * Department of Computer Science and Engineering, University of Science and Technology Chittagong(信息科学与工程系,查塔姆冈科技大学) Department of Electrical and Electronic Engineering, University of Science and Technology Chittagong(电气电子工程系,查塔姆冈科技大学) Faculty of Science, Engineering and Technology, University of Science and Technology Chittagong(科学、工程与技术学院,查塔姆冈科技大学)

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 研究针对时间序列预测,提出结合多种技术的概率预测框架QuantFlow,用反向序列嵌入等进行处理,经实验验证其在多数据上效果好,且联合学习可保护隐私。

Comments 9 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.19618 2026-07-27 cs.CV cs.AI cs.LG 版本更新 81%

The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis

自监督预训练在差分隐私医疗图像分析中的作用

Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia, Behrus Hinrichs-Puladi, Jonas Bienzeisler, Mohamed Alhaskir, Mirabela Rusu, Christiane Kuhl, Sven Nebelung, Daniel Truhn

专题命中 领域大模型 :pretraining(title,abstract);分类 cs.AI、cs.LG

AI总结 本文研究了自监督预训练在差分隐私医疗图像分析中的作用,发现DINOv3初始化在DP下优于ImageNet初始化,但不如领域特定监督预训练。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23908 2026-07-14 cs.AI cs.CL cs.CV cs.NE 81%

In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models

寻找开放性的要素:用大型视觉语言模型复现 Picbreeder

Sam Earle, Kai Arulkumaran, Andrew Dai, Akarsh Kumar, Julian Togelius, Sebastian Risi

机构 * New York University(纽约大学) Massachusetts Institute of Technology(麻省理工学院)

专题命中 领域大模型 :language model(title,abstract);分类 cs.CL、cs.AI

AI总结 本研究通过用前沿视觉语言模型替代人类用户复现 Picbreeder,探索人工智能在无引导发现中的开放性能力,并分析系统输出与人类基线在系统发育复杂性、视觉和语义显著性及新颖性上的差异,同时研究探索性噪声、行为多样性和叙事动量等因素的影响。

Comments 26 pages, 21 figures, to be published at GECCO 2026

Journal ref Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '26), July 13-17, 2026, San José, Costa Rica. ACM, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.06080 2026-07-08 cs.CL cs.AI cs.SI 新提交 81%

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

从蓝图到现实:基于大语言模型的多智能体模拟对普特南社会资本理论的建模与应用

Shiyi Ling, Zhi Zheng, Hui Zheng, Wenjun Xue, Feng Ye, Tong Xu

机构 * University of Science and Technology of China(中国科学技术大学) Anhui University(安徽大学) North Automatic Control Technology Institute(北方自动控制技术研究所)

专题命中 领域大模型 :LLM(title,abstract);分类 cs.CL、cs.AI

AI总结 研究利用基于大语言模型的多智能体模拟框架SocaSim,对普特南社会资本理论进行建模与应用,通过构建特定环境及智能体实验分析智能老年护理挑战,重现宏观模式且具微观因果路径可解释性,弥合了社会科学与计算机科学。

Comments 23 pages, 13 figures, 11 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.30107 2026-06-30 cs.AI cs.LG 81%

Structural Certification for Reliable Physical Design with Language Models

面向语言模型可靠物理设计的结构认证

Nakul Vyas, Iliya D. Stoev

机构 * Heysuvi Labs, LLC(Heysuvi实验室) Institute of Biological and Chemical Systems - Functional Molecular Systems, Karlsruhe Institute of Technology(生物和化学系统研究所-功能分子系统,卡尔斯鲁厄技术大学)

专题命中 领域大模型 :language model(title,abstract);分类 cs.AI、cs.LG

AI总结 提出Physics-Anchored Certification (PHACT)框架,通过提议-认证循环将断言权从模型转移到确定性引擎,在五个科学领域实现零错误认证。

Comments 16 pages, 5 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17117 2026-06-30 cs.CV cs.AI cs.LG 81%

PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science

PlantExpertVQA: 一个用于植物科学中视觉语言模型基准测试的视觉问答数据集

Syed Nazmus Sakib, Nafiul Haque, Mohammad Zabed Hossain, Shifat E. Arman

机构 * Department of Robotics and Mechatronics Engineering, University of Dhaka(达卡大学机器人与机电工程系) Department of Botany, University of Dhaka(达卡大学植物学系)

专题命中 领域大模型 :language model(title,abstract);分类 cs.AI、cs.LG

AI总结 PlantExpertVQA数据集旨在提升视觉语言模型在农业决策中的应用,包含765,186个高质量问答对,涵盖38种作物和89种病害,通过多阶段流程生成并经专家审核,验证了参数高效微调的有效性。

Comments 36 pages, 9 figures, 14 tables and Submitted to Nature Scientific Data

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.24162 2026-06-24 cs.CL cs.LG 新提交 81%

BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks

BehaviorBench: 行为科学任务的基础模型基准测试

Jin Huang, Yutong Xie, Wanli Song, Xingjian Zhang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei

机构 * University of Michigan(密歇根大学) MobLab Stanford University(斯坦福大学) Santa Fe Institute(圣塔菲研究所)

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.CL、cs.LG

AI总结 提出BehaviorBench基准,评估基础模型在行为预测、战略决策、特质推断和行为知识应用四类任务上的个体与分布级表现,发现通用模型个体预测强,而微调的行为模型分布对齐更优。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.16696 2026-06-24 cs.LG cs.AI cs.MM cs.SD 版本更新 81%

FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation

FISHER:多模态工业信号综合表示的基础模型

Pingyi Fan, Anbai Jiang, Shuwei Zhang, Xinhu Zheng, Zhiqiang Lv, Bing Han, Wenrui Liang, Junjie Li, Wei-Qiang Zhang, Yanmin Qian, Xie Chen, Jia Liu

机构 * Department of Electronic Engineering, Tsinghua University(清华大学电子工程系) Institute for Embodied Intelligence and Robotics, Tsinghua University(清华大学智能感知与机器人研究院) Department of Computer Science and Engineering, Shanghai Jiao Tong University(上海交通大学计算机科学与工程系) Huakong AI Plus Company Limited(华冠AIplus有限公司) Didi International Business Group(滴滴国际商务集团)

专题命中 领域大模型 :foundation model(title,abstract);分类 cs.AI、cs.LG

AI总结 针对工业信号分析中的数据异质性(M5问题),提出FISHER基础模型,采用子带建模处理多采样率问题,通过教师-学生自蒸馏预训练,在19个数据集上以较小规模超越24个SOTA编码器。

Comments Accepted by IEEE TII. FISHER open-sourced on https://github.com/jianganbai/FISHER . RMIS open-sourced on https://jianganbai.github.io/RMIS

详情

展开后加载摘要…

URL PDF HTML 收藏