语言大模型 / LLM - arXivDaily 专题

2309.08958 2024-02-01 cs.CL cs.AI 86%

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev, Andrey Kutuzov, Barry Haddow, Kenneth Heafield

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 Findings of ACL: EACL 2024. Added human evaluation and shortened writing

2401.12915 2024-01-24 cs.AI cs.CL cs.CV 86%

Red Teaming Visual Language Models

Mukai Li, Lei Li, Yuwei Yin, Masood Ahmed, Zhenguang Liu, Qi Liu

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

Comments Working in progress

2401.05033 2024-01-11 cs.CL cs.AI 86%

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, Yi Zhang

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

2307.15504 2024-01-09 cs.CL cs.AI 86%

Exploring Format Consistency for Instruction Tuning

Shihao Liang, Runchu Tian, Kunlun Zhu, Yujia Qin, Huadong Wang, Xin Cong, Zhiyuan Liu, Xiaojiang Liu, Maosong Sun

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

2309.01105 2024-01-03 cs.AI cs.CL 86%

A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture

Cheonsu Jeong

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

2308.10253 2023-12-29 cs.CV cs.CL cs.LG 86%

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

Yanda Li, Chi Zhang, Gang Yu, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

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 Project page: https://github.com/icoz69/StableLLAVA

2311.18260 2023-12-22 eess.IV cs.CL cs.CV cs.LG 86%

Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation

Ryutaro Tanno, David G. T. Barrett, Andrew Sellergren, Sumedh Ghaisas, Sumanth Dathathri, Abigail See, Johannes Welbl, Karan Singhal, Shekoofeh Azizi, Tao Tu, Mike Schaekermann, Rhys May, Roy Lee, SiWai Man, Zahra Ahmed, Sara Mahdavi, Yossi Matias, Joelle Barral, Ali Eslami, Danielle Belgrave, Vivek Natarajan, Shravya Shetty, Pushmeet Kohli, Po-Sen Huang, Alan Karthikesalingam, Ira Ktena

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

2310.15539 2023-12-18 cs.CL cs.AI 86%

SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation

Jialing Pan, Adrien Sadé, Jin Kim, Eric Soriano, Guillem Sole, Sylvain Flamant

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

2310.10158 2023-12-15 cs.CL cs.AI 86%

Character-LLM: A Trainable Agent for Role-Playing

Yunfan Shao, Linyang Li, Junqi Dai, Xipeng Qiu

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 To appear at EMNLP 2023; Repo at https://github.com/choosewhatulike/trainable-agents

2312.02798 2023-12-06 cs.LG cs.CL 86%

Weakly Supervised Detection of Hallucinations in LLM Activations

Miriam Rateike, Celia Cintas, John Wamburu, Tanya Akumu, Skyler Speakman

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

2310.03211 2023-11-29 cs.CL cs.AI cs.CV 86%

On the Performance of Multimodal Language Models

Utsav Garg, Erhan Bas

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

2311.08182 2023-11-15 cs.CL cs.LG 86%

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning

Shengguang Wu, Keming Lu, Benfeng Xu, Junyang Lin, Qi Su, Chang Zhou

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

2311.03716 2023-11-08 cs.CL cs.AI cs.CV 86%

LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators

Allen Roush, Emil Zakirov, Artemiy Shirokov, Polina Lunina, Jack Gane, Alexander Duffy, Charlie Basil, Aber Whitcomb, Jim Benedetto, Chris DeWolfe

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

Comments 12 pages, System Demonstration/Industry paper. Preprint

2311.00288 2023-11-02 cs.CL cs.AI 86%

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks

Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng

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 EMNLP 2023 Main

2310.19084 2023-10-31 cs.CL cs.AI 86%

Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention

Changjiang Gao, Shujian Huang, Jixing Li, Jiajun Chen

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

2305.13627 2023-10-25 cs.CL cs.AI 86%

InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, Pascale Fung

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

2310.11003 2023-10-18 cs.CL cs.LG cs.SD eess.AS 86%

Correction Focused Language Model Training for Speech Recognition

Yingyi Ma, Zhe Liu, Ozlem Kalinli

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

2309.06126 2023-09-13 astro-ph.IM astro-ph.CO astro-ph.GA astro-ph.HE cs.CL cs.LG 86%

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Tuan Dung Nguyen, Yuan-Sen Ting, Ioana Ciucă, Charlie O'Neill, Ze-Chang Sun, Maja Jabłońska, Sandor Kruk, Ernest Perkowski, Jack Miller, Jason Li, Josh Peek, Kartheik Iyer, Tomasz Różański, Pranav Khetarpal, Sharaf Zaman, David Brodrick, Sergio J. Rodríguez Méndez, Thang Bui, Alyssa Goodman, Alberto Accomazzi, Jill Naiman, Jesse Cranney, Kevin Schawinski, UniverseTBD

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

Comments 6 pages, 3 figures, submitted to IJCNLP-AACL 2023. Comments are welcome. The model can be found on Hugging Face - https://huggingface.co/universeTBD/astrollama

2308.13768 2023-08-29 cs.CL cs.LG 86%

Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content

Charles O'Neill, Jack Miller, Ioana Ciuca, Yuan-Sen Ting, Thang Bui

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

2306.14101 2023-06-27 cs.LG cs.AI 86%

Language models are weak learners

Hariharan Manikandan, Yiding Jiang, J Zico Kolter

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

Comments 23 pages, 6 figures

2304.03609 2023-06-26 cs.CL cs.LG 86%

Revisiting Automated Prompting: Are We Actually Doing Better?

Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal

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

2306.05425 2023-06-09 cs.CV cs.AI cs.CL cs.HC 86%

MIMIC-IT: Multi-Modal In-Context Instruction Tuning

Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Fanyi Pu, Jingkang Yang, Chunyuan Li, Ziwei Liu

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 Project page: https://otter-ntu.github.io/ Dataset & code: https://github.com/Luodian/otter Initial release, work in progress

2304.13731 2023-05-30 eess.AS cs.AI cs.CL cs.SD 86%

Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model

Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria

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 https://github.com/declare-lab/tango

2305.14483 2023-05-25 cs.CL cs.LG 86%

Language Model Self-improvement by Reinforcement Learning Contemplation

Jing-Cheng Pang, Pengyuan Wang, Kaiyuan Li, Xiong-Hui Chen, Jiacheng Xu, Zongzhang Zhang, Yang Yu

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

2305.11460 2023-05-22 cs.CL cs.AI cs.MA 86%

Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions

Shiyao Ding, Takayuki Ito

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

2304.08085 2023-04-18 cs.CL cs.AI 86%

InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction

Xiao Wang, Weikang Zhou, Can Zu, Han Xia, Tianze Chen, Yuansen Zhang, Rui Zheng, Junjie Ye, Qi Zhang, Tao Gui, Jihua Kang, Jingsheng Yang, Siyuan Li, Chunsai Du

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

2304.03277 2023-04-07 cs.CL cs.AI 86%

Instruction Tuning with GPT-4

Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao

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

Comments 8 pages. Work in progress. Project page: https://instruction-tuning-with-gpt-4.github.io

2209.14500 2023-02-07 cs.LG cs.CL 86%

Bidirectional Language Models Are Also Few-shot Learners

Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli, Noah Constant, Colin Raffel, Chris Callison-Burch

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

Comments To appear at ICLR 2023

2211.15006 2022-11-29 cs.LG cs.CL 86%

Fine-tuning language models to find agreement among humans with diverse preferences

Michiel A. Bakker, Martin J. Chadwick, Hannah R. Sheahan, Michael Henry Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matthew M. Botvinick, Christopher Summerfield

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

2604.00342 2026-04-02 cs.LG 86%

Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA

一个token足够吗？基于LLM的图QA的图池化token

Ankit Grover, Lodovico Giaretta, Rémi Bourgerie, Sarunas Girdzijauskas

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

AI总结本文提出通过多token池化和全局注意力机制改进图与LLM的接口，通过实验表明LoRA可稳定特定层次投影，使压缩表示在WebQSP上达到73%的Hit@1，揭示图QA基准存在表示饱和问题。

Comments Accepted at LREC, KG-LLM Workshop 2026

1. 指令微调 11585 篇

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Red Teaming Visual Language Models

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

Exploring Format Consistency for Instruction Tuning

A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation

SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation

Character-LLM: A Trainable Agent for Role-Playing

Weakly Supervised Detection of Hallucinations in LLM Activations

On the Performance of Multimodal Language Models

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning

LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks

Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention

InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

Correction Focused Language Model Training for Speech Recognition

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content

Language models are weak learners

Revisiting Automated Prompting: Are We Actually Doing Better?

MIMIC-IT: Multi-Modal In-Context Instruction Tuning

Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model

Language Model Self-improvement by Reinforcement Learning Contemplation

Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions

InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction

Instruction Tuning with GPT-4

Bidirectional Language Models Are Also Few-shot Learners

Fine-tuning language models to find agreement among humans with diverse preferences

Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA