语言大模型 / LLM - arXivDaily 专题

2407.13511 2024-07-19 cs.CL 77%

Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks

Samy Ateia, Udo Kruschwitz

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

Comments Version as accepted at the BioASQ Lab at CLEF 2024

2407.12281 2024-07-19 cs.CR cs.AI 77%

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou, Farhan Ahmed, Ling Cai, Nathalie Baracaldo

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

Comments 18 pages, 11 figures

2407.09287 2024-07-15 cs.AI 77%

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments

Zoya Volovikova, Alexey Skrynnik, Petr Kuderov, Aleksandr I. Panov

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

2407.08607 2024-07-12 cs.CL 77%

Turn-Level Empathy Prediction Using Psychological Indicators

Shaz Furniturewala, Kokil Jaidka

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

2403.09740 2024-07-12 cs.SE cs.AI 77%

Teaching Machines to Code: Smart Contract Translation with LLMs

Rabimba Karanjai, Lei Xu, Weidong Shi

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

2405.03138 2024-07-11 cs.CL 77%

CRAFT: Extracting and Tuning Cultural Instructions from the Wild

Bin Wang, Geyu Lin, Zhengyuan Liu, Chengwei Wei, Nancy F. Chen

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

Comments Aceepted to ACL 2024 Workshop - C3NLP (Workshop on Cross-Cultural Considerations in NLP)

2407.06955 2024-07-10 cs.CR cs.CL 77%

ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization

Wai Man Si, Michael Backes, Yang Zhang

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

2407.06196 2024-07-10 cs.CV cs.AI 77%

Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry

Jing Jiang, Yiran Ling, Binzhu Li, Pengxiang Li, Junming Piao, Yu Zhang

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

Comments 13 pages, 7 figures

2407.05733 2024-07-09 cs.CL cs.CY 77%

Is GPT-4 Alone Sufficient for Automated Essay Scoring?: A Comparative Judgment Approach Based on Rater Cognition

Seungju Kim, Meounggun Jo

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

Comments 16 pages, 3 figures, Learning @ Scale 2024

2407.04434 2024-07-08 cs.CL 77%

From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs

Marion Bartl, Susan Leavy

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

Comments 10 pages, 5 tables; to appear in Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing at ACL 2024

2406.17377 2024-06-26 cs.CL 77%

A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs

Vaibhav Singh, Amrith Krishna, Karthika NJ, Ganesh Ramakrishnan

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

2406.13476 2024-06-26 cs.CL 77%

LLMs Are Zero-Shot Context-Aware Simultaneous Translators

Roman Koshkin, Katsuhito Sudoh, Satoshi Nakamura

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

2402.14968 2024-06-21 cs.CR cs.CL 77%

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Yixuan Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao

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

2402.16602 2024-06-21 cs.CL 77%

Rethinking Negative Instances for Generative Named Entity Recognition

Yuyang Ding, Juntao Li, Pinzheng Wang, Zecheng Tang, Bowen Yan, Min Zhang

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

Comments ACL 2024 Findings

2402.11750 2024-06-19 cs.CL 77%

In-Context Learning Demonstration Selection via Influence Analysis

Vinay M. S., Minh-Hao Van, Xintao Wu

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

Comments 11 pages, 1 figure, and 6 tables

2406.07759 2024-06-13 cs.CL 77%

LT4SG@SMM4H24: Tweets Classification for Digital Epidemiology of Childhood Health Outcomes Using Pre-Trained Language Models

Dasun Athukoralage, Thushari Atapattu, Menasha Thilakaratne, Katrina Falkner

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

Comments Submitted for the 9th Social Media Mining for Health Research and Applications Workshop and Shared Tasks- Large Language Models (LLMs) and Generalizability for Social Media NLP

2406.05690 2024-06-11 cs.CL 77%

MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation

Yan Ma, Yu Qiao, Pengfei Liu

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

Comments ACL 2024, camera-ready

2406.02806 2024-06-11 cs.LG math.OC stat.ML 77%

Randomized Geometric Algebra Methods for Convex Neural Networks

Yifei Wang, Sungyoon Kim, Paul Chu, Indu Subramaniam, Mert Pilanci

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

2405.07798 2024-06-11 cs.CV cs.AI 77%

FreeVA: Offline MLLM as Training-Free Video Assistant

Wenhao Wu

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

Comments Preprint. Work in progress

2401.14556 2024-06-07 cs.CL 77%

Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling

David Dukić, Jan Šnajder

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

Comments Accepted at ACL 2024 Findings

2404.14367 2024-06-04 cs.LG 77%

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar

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

Comments International Conference on Machine Learning (ICML), 2024

2402.11867 2024-05-29 cs.LG math.OC 77%

LoRA Training in the NTK Regime has No Spurious Local Minima

Uijeong Jang, Jason D. Lee, Ernest K. Ryu

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

Comments 23 pages

2402.09179 2024-05-29 cs.CR cs.LG 77%

Instruction Backdoor Attacks Against Customized LLMs

Rui Zhang, Hongwei Li, Rui Wen, Wenbo Jiang, Yuan Zhang, Michael Backes, Yun Shen, Yang Zhang

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

2309.00916 2024-05-29 cs.CL cs.SD eess.AS 77%

BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

Chen Wang, Minpeng Liao, Zhongqiang Huang, Jinliang Lu, Junhong Wu, Yuchen Liu, Chengqing Zong, Jiajun Zhang

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

2402.01621 2024-05-28 cs.LG 77%

Stochastic Two Points Method for Deep Model Zeroth-order Optimization

Yijiang Pang, Jiayu Zhou

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

2405.16482 2024-05-28 cs.CL 77%

DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakers

Abderrahman Skiredj, Ferdaous Azhari, Ismail Berrada, Saad Ezzini

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

2405.16229 2024-05-28 cs.CL cs.CR 77%

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

Chak Tou Leong, Yi Cheng, Kaishuai Xu, Jian Wang, Hanlin Wang, Wenjie Li

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

Comments work in progress

2405.15202 2024-05-27 cs.CL cs.CR 77%

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety

Yu Fu, Wen Xiao, Jia Chen, Jiachen Li, Evangelos Papalexakis, Aichi Chien, Yue Dong

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

Comments accepted to NAACL2024 TrustNLP workshop

2311.02805 2024-05-24 cs.CL 77%

Tailoring Self-Rationalizers with Multi-Reward Distillation

Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu, Liunian Harold Li, Aaron Chan, Jack Hessel, Yejin Choi, Xiang Ren

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

Journal ref The Twelfth International Conference on Learning Representations, 2024

2405.07467 2024-05-14 cs.CL 77%

MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation

Dongjun Lee, Choongwon Park, Jaehyuk Kim, Heesoo Park

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

1. 指令微调 11714 篇

Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments

Turn-Level Empathy Prediction Using Psychological Indicators

Teaching Machines to Code: Smart Contract Translation with LLMs

CRAFT: Extracting and Tuning Cultural Instructions from the Wild

ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization

Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry

Is GPT-4 Alone Sufficient for Automated Essay Scoring?: A Comparative Judgment Approach Based on Rater Cognition

From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs

A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs

LLMs Are Zero-Shot Context-Aware Simultaneous Translators

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

Rethinking Negative Instances for Generative Named Entity Recognition

In-Context Learning Demonstration Selection via Influence Analysis

LT4SG@SMM4H24: Tweets Classification for Digital Epidemiology of Childhood Health Outcomes Using Pre-Trained Language Models

MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation

Randomized Geometric Algebra Methods for Convex Neural Networks

FreeVA: Offline MLLM as Training-Free Video Assistant

Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

LoRA Training in the NTK Regime has No Spurious Local Minima

Instruction Backdoor Attacks Against Customized LLMs

BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

Stochastic Two Points Method for Deep Model Zeroth-order Optimization

DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakers

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety

Tailoring Self-Rationalizers with Multi-Reward Distillation

MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation