语言大模型 / LLM - arXivDaily 专题

2410.01869 2024-10-04 cs.DB cs.AI cs.SE 85%

Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement

Shouvon Sarker, Xishuang Dong, Xiangfang Li, Lijun Qian

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

2404.19335 2024-10-04 cs.CL 85%

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation

Xiaoming Liu, Chen Liu, Zhaohan Zhang, Chengzhengxu Li, Longtian Wang, Yu Lan, Chao Shen

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

Comments EMNLP 2024 Findings

2311.08369 2024-10-02 cs.CL 85%

How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection

Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki

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

Comments EMNLP 2024 Findings camera ready. Dataset available at https://github.com/ryuryukke/HowYouPromptMatters

2409.16563 2024-09-26 cs.AI 85%

Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels

Yishu Wei, Xindi Wang, Hanley Ong, Yiliang Zhou, Adam Flanders, George Shih, Yifan Peng

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

2401.02731 2024-09-25 cs.AI 85%

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Haoyuan Wu, Haisheng Zheng, Zhuolun He, Bei Yu

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2401.08315 2024-08-14 cs.CL 85%

Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening

Chengguang Gan, Qinghao Zhang, Tatsunori Mori

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

Comments Accept by Journal of Information Processing,(2024), 18 pages, 19 figures

2408.05882 2024-08-13 cs.CL 85%

Creating Arabic LLM Prompts at Scale

Abdelrahman El-Sheikh, Ahmed Elmogtaba, Kareem Darwish, Muhammad Elmallah, Ashraf Elneima, Hassan Sawaf

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

2405.20089 2024-08-07 cs.CL 85%

The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities

David Stap, Eva Hasler, Bill Byrne, Christof Monz, Ke Tran

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

Comments Accepted to ACL 2024 (long, main). Latest version includes link to the IdiomsInCtx-MT dataset

2407.17813 2024-07-26 cs.CV cs.AI 85%

Enhancing Model Performance: Another Approach to Vision-Language Instruction Tuning

Vedanshu, MM Tripathi, Bhavnesh Jaint

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

2405.06649 2024-07-15 q-bio.BM cs.LG q-bio.MN 85%

ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction

Mingyu Jin, Haochen Xue, Zhenting Wang, Boming Kang, Ruosong Ye, Kaixiong Zhou, Mengnan Du, Yongfeng Zhang

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

Comments Accepted by COLM 2024

2401.09181 2024-06-28 cs.LG 85%

Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer

Junhao Zheng, Qianli Ma, Zhen Liu, Binquan Wu, Huawen Feng

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2403.06131 2024-06-21 cs.CR cs.AI 85%

FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning

Zhuo Zhang, Jingyuan Zhang, Jintao Huang, Lizhen Qu, Hongzhi Zhang, Qifan Wang, Xun Zhou, Zenglin Xu

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Work in progress

2406.06822 2024-06-12 cs.CR cs.AI cs.SE 85%

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong

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

Comments To appear in USENIX Security '24

2406.05249 2024-06-11 cs.CE cs.AI 85%

A Language Model-Guided Framework for Mining Time Series with Distributional Shifts

Haibei Zhu, Yousef El-Laham, Elizabeth Fons, Svitlana Vyetrenko

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

2402.11517 2024-06-07 cs.CL 85%

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

Zijin Hong, Zheng Yuan, Hao Chen, Qinggang Zhang, Feiran Huang, Xiao Huang

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

Comments Accepted to ACL2024 Findings

2310.00901 2024-06-05 cs.CL 85%

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning

Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to ACL Findings 2024

2405.18035 2024-05-30 cs.CL 85%

Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis

Guangmin Zheng, Jin Wang, Liang-Chih Yu, Xuejie Zhang

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments ACL Findings 2024

2405.16579 2024-05-28 cs.CL 85%

Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity

Shanghaoran Quan

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

2405.12528 2024-05-22 cs.CL 85%

SirLLM: Streaming Infinite Retentive LLM

Yao Yao, Zuchao Li, Hai Zhao

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

2402.06221 2024-05-09 cs.CL cs.IR 85%

ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement

Saurabh Bhausaheb Zinjad, Amrita Bhattacharjee, Amey Bhilegaonkar, Huan Liu

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

Comments Accepted to SIGIR 2024 (Demo)

2310.16960 2024-05-06 cs.LG cs.CR 85%

Privately Aligning Language Models with Reinforcement Learning

Fan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim

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

Comments Accepted at ICLR 2024

2311.08896 2024-04-30 cs.CL 85%

HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation

Junyi Bian, Xiaolei Qin, Wuhe Zou, Mengzuo Huang, Congyi Luo, Ke Zhang, Weidong Zhang

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

2404.16670 2024-04-26 cs.CV cs.AI 85%

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning

Hongxia Xie, Chu-Jun Peng, Yu-Wen Tseng, Hung-Jen Chen, Chan-Feng Hsu, Hong-Han Shuai, Wen-Huang Cheng

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted by CVPR 2024

2404.07456 2024-04-12 cs.AI cs.MA 85%

WESE: Weak Exploration to Strong Exploitation for LLM Agents

Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen

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

2305.07490 2024-04-08 cs.CL cs.CV 85%

ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter

Zhengqing Yuan, Yunhong He, Kun Wang, Yanfang Ye, Lichao Sun

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

2310.15851 2024-03-25 cs.CL 85%

Self-Guard: Empower the LLM to Safeguard Itself

Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, Qingwei Lin, Kam-Fai Wong

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

2309.11235 2024-03-19 cs.CL 85%

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Guan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, Yang Liu

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

2310.04963 2024-03-12 cs.AI 85%

LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation

Christian Munley, Aaron Jarmusch, Sunita Chandrasekaran

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

2403.05338 2024-03-11 cs.CL 85%

Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings

Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu

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

2403.03017 2024-03-06 cs.AI 85%

OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following

Haochen Shi, Zhiyuan Sun, Xingdi Yuan, Marc-Alexandre Côté, Bang Liu

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

1. 指令微调 11667 篇

Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation

How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection

Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening

Creating Arabic LLM Prompts at Scale

The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities

Enhancing Model Performance: Another Approach to Vision-Language Instruction Tuning

ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction

Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer

FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

A Language Model-Guided Framework for Mining Time Series with Distributional Shifts

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning

Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis

Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity

SirLLM: Streaming Infinite Retentive LLM

ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement

Privately Aligning Language Models with Reinforcement Learning

HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning

WESE: Weak Exploration to Strong Exploitation for LLM Agents

ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter

Self-Guard: Empower the LLM to Safeguard Itself

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation

Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings

OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following