语言大模型 / LLM - arXivDaily 专题

2311.02236 2023-11-07 cs.CV cs.AI cs.CL cs.LG 82%

Robust Fine-Tuning of Vision-Language Models for Domain Generalization

Kevin Vogt-Lowell, Noah Lee, Theodoros Tsiligkaridis, Marc Vaillant

专题命中指令微调：language model(title)；foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments In proceedings of the 27th IEEE High Performance Extreme Computing Conference

2302.04858 2023-10-24 cs.CV cs.AI cs.CL cs.IR cs.LG 82%

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Ming-Yu Liu, Yuke Zhu, Mohammad Shoeybi, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Findings of EMNLP 2023

2310.06248 2023-10-11 eess.AS 82%

Discriminative Speech Recognition Rescoring with Pre-trained Language Models

Prashanth Gurunath Shivakumar, Jari Kolehmainen, Yile Gu, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

专题命中指令微调：language model(title,abstract)；large language model(abstract)

Comments ASRU 2023

2309.01155 2023-09-25 cs.CV 82%

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Cheng Shi, Sibei Yang

专题命中指令微调：language model(title,abstract)；prompting(abstract)

Comments ICCV 2023; Project Page:https://chengshiest.github.io/logo

2305.17446 2023-08-02 cs.CL cs.AI cs.LG 82%

Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models

Zhong Zhang, Bang Liu, Junming Shao

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2023 (main conference, long paper)

2306.15926 2023-06-29 cs.CL cs.AI cs.LG 82%

Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio

Allen Roush, Sanjay Basu, Akshay Moorthy, Dmitry Dubovoy

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in the proceedings of the 2nd Workshop on When Creative AI Meets Conversational AI (CAI2), COLING 2022, 6 pages, System Demonstration Paper

2304.09058 2023-06-21 cs.CL cs.AI cs.DB cs.IR cs.LG 82%

Revisiting k-NN for Fine-tuning Pre-trained Language Models

Lei Li, Jing Chen, Bozhong Tian, Ningyu Zhang

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments CCL 2023

2304.03472 2023-04-18 cs.CR 82%

Does Prompt-Tuning Language Model Ensure Privacy?

Shangyu Xie, Wei Dai, Esha Ghosh, Sambuddha Roy, Dan Schwartz, Kim Laine

专题命中指令微调：language model(title,abstract)；large language model(abstract)

Comments 8 pages

2302.11773 2023-02-24 cs.CR 82%

Detecting software vulnerabilities using Language Models

Marwan Omar

专题命中指令微调：language model(title,abstract)；large language model(abstract)

2301.13688 2023-02-15 cs.AI cs.CL cs.LG 82%

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

Shayne Longpre, Le Hou, Tu Vu, Albert Webson, Hyung Won Chung, Yi Tay, Denny Zhou, Quoc V. Le, Barret Zoph, Jason Wei, Adam Roberts

专题命中指令微调：instruction tuning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2211.15195 2022-11-29 cs.CL cs.AI cs.LG 82%

Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning

Witold Sosnowski, Karolina Seweryn, Anna Wróblewska, Piotr Gawrysiak

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2205.11726 2022-10-27 cs.CL cs.AI cs.LG 82%

On the Role of Bidirectionality in Language Model Pre-Training

Mikel Artetxe, Jingfei Du, Naman Goyal, Luke Zettlemoyer, Ves Stoyanov

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Findings of EMNLP 2022

2210.10041 2022-10-20 cs.CL cs.AI cs.LG 82%

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning

Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2022 camera-ready

2210.03378 2022-10-10 cs.CL cs.AI cs.LG 82%

UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation

Injy Sarhan, Pablo Mosteiro, Marco Spruit

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Journal ref In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 271-281, Seattle, United States. Association for Computational Linguistics

2206.14574 2022-06-30 cs.CL cs.AI cs.LG 82%

Knowledge Graph Fusion for Language Model Fine-tuning

Nimesh Bhana, Terence L. van Zyl

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Submitted to ISCMI 2022

2205.05124 2022-05-12 cs.CL cs.AI cs.LG 82%

Extracting Latent Steering Vectors from Pretrained Language Models

Nishant Subramani, Nivedita Suresh, Matthew E. Peters

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACL2022 Findings; 16 pages (9 pages plus references and appendices); Code: https://github.com/nishantsubramani/steering_vectors; Some text overlap with arXiv:2008.09049

2111.02687 2021-11-05 cs.CL cs.AI cs.LG 82%

CoreLM: Coreference-aware Language Model Fine-Tuning

Nikolaos Stylianou, Ioannis Vlahavas

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 12 pages, 2 figures, Accepted at Fourth Workshop on Computational Models of Reference, Anaphora and Coreference

2104.08027 2021-09-10 cs.CL cs.AI cs.LG 82%

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders

Fangyu Liu, Ivan Vulić, Anna Korhonen, Nigel Collier

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2021 camera-ready version

2010.02329 2021-03-23 cs.CL cs.AI cs.LG 82%

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICLR 2021. 23 pages, 9 tables, 3 figures

2101.09688 2021-02-17 cs.CL cs.AI cs.LG cs.NE 82%

Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models

Daniel de Vassimon Manela, David Errington, Thomas Fisher, Boris van Breugel, Pasquale Minervini

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)

1912.13283 2020-11-20 cs.CL cs.AI cs.LG 82%

oLMpics -- On what Language Model Pre-training Captures

Alon Talmor, Yanai Elazar, Yoav Goldberg, Jonathan Berant

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments TACL 2020

2010.11967 2020-10-26 cs.CL cs.AI cs.LG 82%

Language Models are Open Knowledge Graphs

Chenguang Wang, Xiao Liu, Dawn Song

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 30 pages, 32 figures, 3 tables

2010.11506 2020-10-23 cs.CL cs.AI cs.LG 82%

Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao, Chao Zhang

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP2020 long paper

2009.05603 2020-09-18 cs.CL cs.AI cs.IR cs.LG 82%

UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction

Andrei-Marius Avram, Dumitru-Clementin Cercel, Costin-Gabriel Chiru

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

1912.02164 2020-03-04 cs.CL cs.AI cs.LG 82%

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2020 camera ready

2507.12414 2026-05-01 cs.CV cs.AI cs.LG cs.RO 82%

AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models

AutoVDC：利用视觉-语言模型实现自动化视觉数据清洗

Santosh Vasa, Aditi Ramadwar, Jnana Rama Krishna Darabattula, Md Zafar Anwar, Stanislaw Antol, Andrei Vatavu, Thomas Monninger, Sihao Ding

机构 * Mercedes-Benz Research & Development North America（梅赛德斯-奔驰北美研发公司）； University of Stuttgart, Institute for Artificial Intelligence（斯图加特大学人工智能研究所）

专题命中指令微调：language model(title,abstract)；分类 cs.AI、cs.LG；foundation model(comments)

AI总结本文提出AutoVDC框架，利用视觉-语言模型自动识别视觉数据集中的错误标注，提升数据质量。通过KITTI和nuImages数据集验证，展示了方法在错误检测和数据清洗中的高性能。

Comments Accepted to IV 2026 Drive-X Foundation Models for Autonomous Driving (Oral presentation)

2507.22469 2025-07-31 cs.CV cs.AI cs.LG 82%

Visual Language Models as Zero-Shot Deepfake Detectors

Viacheslav Pirogov

专题命中指令微调：language model(title,abstract)；分类 cs.AI、cs.LG；foundation model(comments)

Comments Accepted to the ICML 2025 Workshop on Reliable and Responsible Foundation Models

2407.03482 2024-07-11 cs.CV cs.AI cs.LG 82%

Domain-Aware Fine-Tuning of Foundation Models

Ugur Ali Kaplan, Margret Keuper, Anna Khoreva, Dan Zhang, Yumeng Li

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted at ICML 2024 Workshop on Foundation Models in the Wild

2403.04529 2024-03-08 cs.LG cs.AI cs.DC 82%

Enhancing Data Quality in Federated Fine-Tuning of Foundation Models

Wanru Zhao, Yaxin Du, Nicholas Donald Lane, Siheng Chen, Yanfeng Wang

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted at ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models (DPFM)

2608.19938 2026-08-21 cs.CR cs.LG 新提交 81%

From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs

从噪声到信号：利用具备端点特定日志的大语言模型改进安全日志异常检测

Christopher Henshaw, Gour Karmakar

专题命中指令微调：LLM(summary_cn,abstract)；分类 cs.LG

AI总结本研究开发基于指令的LLM分类框架，结合端点特定日志，经实验验证Meta Llama 3.1 8B Instruct在安全日志异常检测中性能优于Wazuh、OpenSearch等方法。

Comments The paper contains 35 pages and 3 figures. The paper has not been submitted or published in any conference or journal. The authors have an aim to publish it in a journal

1. 指令微调 11619 篇

Robust Fine-Tuning of Vision-Language Models for Domain Generalization

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

Discriminative Speech Recognition Rescoring with Pre-trained Language Models

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models

Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio

Revisiting k-NN for Fine-tuning Pre-trained Language Models

Does Prompt-Tuning Language Model Ensure Privacy?

Detecting software vulnerabilities using Language Models

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning

On the Role of Bidirectionality in Language Model Pre-Training

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning

UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation

Knowledge Graph Fusion for Language Model Fine-tuning

Extracting Latent Steering Vectors from Pretrained Language Models

CoreLM: Coreference-aware Language Model Fine-Tuning

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models

oLMpics -- On what Language Model Pre-training Captures

Language Models are Open Knowledge Graphs

Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models

Visual Language Models as Zero-Shot Deepfake Detectors

Domain-Aware Fine-Tuning of Foundation Models

Enhancing Data Quality in Federated Fine-Tuning of Foundation Models

From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs