语言大模型 / LLM - arXivDaily 专题

2402.04049 2024-12-18 cs.CL cs.AI 86%

Systematic Biases in LLM Simulations of Debates

Amir Taubenfeld, Yaniv Dover, Roi Reichart, Ariel Goldstein

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

Comments Published as a conference paper at EMNLP 2024

2412.10689 2024-12-17 cs.CL cs.AI 86%

Learning to Verify Summary Facts with Fine-Grained LLM Feedback

Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim, Taewon Yun, Hwanjun Song

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

Comments Accepted at COLING 2025

2405.19732 2024-12-05 cs.CV cs.CL cs.LG 86%

LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning

Zixian Guo, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, Wangmeng Zuo

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

2410.12361 2024-12-04 cs.AI cs.CL 86%

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Yaxi Lu, Shenzhi Yang, Cheng Qian, Guirong Chen, Qinyu Luo, Yesai Wu, Huadong Wang, Xin Cong, Zhong Zhang, Yankai Lin, Weiwen Liu, Yasheng Wang, Zhiyuan Liu, Fangming Liu, Maosong Sun

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

Comments 9 pages, 4 figures

2411.13405 2024-11-21 cs.CL cs.LG 86%

On the Way to LLM Personalization: Learning to Remember User Conversations

Lucie Charlotte Magister, Katherine Metcalf, Yizhe Zhang, Maartje ter Hoeve

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

Comments 16 pages, 6 tables, 3 figures

2411.10696 2024-11-19 cs.LG cs.AI 86%

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization

Huaqin Zhao, Jiaxi Li, Yi Pan, Shizhe Liang, Xiaofeng Yang, Wei Liu, Xiang Li, Fei Dou, Tianming Liu, Jin Lu

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

2411.07070 2024-11-13 cs.CL cs.AI 86%

On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models

Qian Sun, Hanpeng Wu, Xi Sheryl Zhang

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

2411.00686 2024-11-04 cs.CL cs.AI 86%

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

Minki Kang, Sung Ju Hwang, Gibbeum Lee, Jaewoong Cho

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

Comments NeurIPS 2024

2410.08048 2024-10-11 cs.LG cs.CL 86%

VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers

Jianing Qi, Hao Tang, Zhigang Zhu

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

2410.05434 2024-10-10 cs.LG cs.AI 86%

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

Sanjiban Choudhury, Paloma Sodhi

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

Comments 34 pages, 6 figures, 5 tables

2409.17972 2024-10-01 cs.CL cs.LG 86%

BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search

Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Conghui He, Zenan Zhou, Wentao Zhang

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

2402.18334 2024-09-12 cs.CL cs.LG 86%

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation

Nihal V. Nayak, Yiyang Nan, Avi Trost, Stephen H. Bach

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

Comments ACL Findings 2024

2409.03346 2024-09-06 cs.CL cs.AI 86%

Sketch: A Toolkit for Streamlining LLM Operations

Xin Jiang, Xiang Li, Wenjia Ma, Xuezhi Fang, Yiqun Yao, Naitong Yu, Xuying Meng, Peng Han, Jing Li, Aixin Sun, Yequan Wang

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

2309.04565 2024-09-04 cs.LG cs.AI 86%

A Versatile Graph Learning Approach through LLM-based Agent

Lanning Wei, Huan Zhao, Xiaohan Zheng, Zhiqiang He, Quanming Yao

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

2408.10174 2024-08-27 cs.LG cs.AI 86%

SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models

Anke Tang, Li Shen, Yong Luo, Shuai Xie, Han Hu, Lefei Zhang, Bo Du, Dacheng Tao

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

Comments Code is available at https://github.com/tanganke/fusion_bench

2408.12779 2024-08-26 cs.CL cs.AI 86%

Investigating LLM Applications in E-Commerce

Chester Palen-Michel, Ruixiang Wang, Yipeng Zhang, David Yu, Canran Xu, Zhe Wu

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

2406.14322 2024-08-19 cs.CL cs.CR cs.LG 86%

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Daogao Liu, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

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

Comments Published as a conference paper at COLM 2024

2401.05799 2024-08-15 cs.CL cs.AI cs.MA q-fin.GN 86%

Designing Heterogeneous LLM Agents for Financial Sentiment Analysis

Frank Xing

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

Comments 15 pages

2401.10660 2024-08-07 cs.CL cs.AI 86%

Accelerating Multilingual Language Model for Excessively Tokenized Languages

Jimin Hong, Gibbeum Lee, Jaewoong Cho

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

Comments Accepted to ACL 2024 Findings

2408.02044 2024-08-06 cs.CL cs.AI 86%

Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages

Tomáš Filip, Martin Pavlíček, Petr Sosík

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

Comments 18 pages, 4 figures

2405.06093 2024-08-06 cs.LG cs.CL 86%

Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection

Bhawesh Kumar, Jonathan Amar, Eric Yang, Nan Li, Yugang Jia

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

Comments 23 pages. Published in MLHC 2024

2408.00960 2024-08-05 cs.CL cs.AI cs.IR 86%

PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting

Liam Hebert, Krishna Sayana, Ambarish Jash, Alexandros Karatzoglou, Sukhdeep Sodhi, Sumanth Doddapaneni, Yanli Cai, Dima Kuzmin

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

2402.05119 2024-07-16 cs.CL cs.AI 86%

A Closer Look at the Limitations of Instruction Tuning

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S, Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha

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

Comments Accepted to ICML 2024

2406.17706 2024-06-26 cs.LG cs.CL cs.DC 86%

FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model

Feijie Wu, Zitao Li, Yaliang Li, Bolin Ding, Jing Gao

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

Comments KDD 2024

2406.13009 2024-06-21 cs.CL cs.AI 86%

Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors

Alex Chandler, Devesh Surve, Hui Su

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

2406.11353 2024-06-18 cs.LG cs.CL 86%

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Guanjie Chen, Xinyu Zhao, Tianlong Chen, Yu Cheng

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

Comments 9 pages, 8 figures, camera ready on ICML2024

2311.03099 2024-06-14 cs.CL cs.LG 86%

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li

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

Comments Accepted at ICML 2024

2406.05255 2024-06-11 cs.CL cs.AI 86%

Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers

Lütfi Kerem Senel, Besnik Fetahu, Davis Yoshida, Zhiyu Chen, Giuseppe Castellucci, Nikhita Vedula, Jason Choi, Shervin Malmasi

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

Comments Accepted at ACL 2024 Main Proceedings

2405.19744 2024-05-31 cs.CL cs.AI 86%

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions

Chong Li, Wen Yang, Jiajun Zhang, Jinliang Lu, Shaonan Wang, Chengqing Zong

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

Comments ACL 2024. Our codes, data and model weights are available at https://github.com/ZNLP/X-Instruction

2405.15928 2024-05-28 q-bio.QM cs.AI cs.LG 86%

PatchProt: Hydrophobic patch prediction using protein foundation models

Dea Gogishvili, Emmanuel Minois-Genin, Jan van Eck, Sanne Abeln

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

1. 指令微调 11667 篇

Systematic Biases in LLM Simulations of Debates

Learning to Verify Summary Facts with Fine-Grained LLM Feedback

LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

On the Way to LLM Personalization: Learning to Remember User Conversations

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization

On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation

Sketch: A Toolkit for Streamlining LLM Operations

A Versatile Graph Learning Approach through LLM-based Agent

SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models

Investigating LLM Applications in E-Commerce

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Designing Heterogeneous LLM Agents for Financial Sentiment Analysis

Accelerating Multilingual Language Model for Excessively Tokenized Languages

Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages

Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection

PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting

A Closer Look at the Limitations of Instruction Tuning

FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model

Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions

PatchProt: Hydrophobic patch prediction using protein foundation models