语言大模型 / LLM - arXivDaily 专题

2311.09665 2024-02-19 cs.CL 85%

The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents

Yun-Shiuan Chuang, Siddharth Suresh, Nikunj Harlalka, Agam Goyal, Robert Hawkins, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy T. Rogers

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

2311.08711 2024-02-13 cs.CL 85%

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning

Zhihan Zhang, Dong-Ho Lee, Yuwei Fang, Wenhao Yu, Mengzhao Jia, Meng Jiang, Francesco Barbieri

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

2402.06125 2024-02-12 cs.CL 85%

Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method

Joshua Zingale, Jugal Kalita

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

Comments To be published in the main proceedings of the Association for Computational Linguistics, European Chapter (EACL 2024)

2402.04636 2024-02-08 cs.CL 85%

TransLLaMa: LLM-based Simultaneous Translation System

Roman Koshkin, Katsuhito Sudoh, Satoshi Nakamura

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

2308.12950 2024-02-02 cs.CL 85%

Code Llama: Open Foundation Models for Code

Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Défossez, Jade Copet, Faisal Azhar, Hugo Touvron, Louis Martin, Nicolas Usunier, Thomas Scialom, Gabriel Synnaeve

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

2305.05644 2024-01-30 cs.CL cs.DC cs.SY eess.SY 85%

Towards Building the Federated GPT: Federated Instruction Tuning

Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li, Ruiyi Zhang, Tong Yu, Yufan Zhou, Guoyin Wang, Yiran 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 Project page: https://github.com/JayZhang42/FederatedGPT-Shepherd

2311.07957 2024-01-30 cs.SE cs.LG 85%

Language Models are Better Bug Detector Through Code-Pair Classification

Kamel Alrashedy, Ahmed Binjahlan

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

2401.07612 2024-01-17 cs.CR cs.AI 85%

Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications

Xuchen Suo

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

2401.03082 2024-01-09 cs.AI 85%

UMIE: Unified Multimodal Information Extraction with Instruction Tuning

Lin Sun, Kai Zhang, Qingyuan Li, Renze Lou

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

2312.13179 2023-12-21 cs.CL 85%

Contextual Code Switching for Machine Translation using Language Models

Arshad Kaji, Manan Shah

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

Comments 4 pages, 1 figure, 2 tables

2307.01003 2023-12-19 cs.CV cs.CL 85%

Visual Instruction Tuning with Polite Flamingo

Delong Chen, Jianfeng Liu, Wenliang Dai, Baoyuan Wang

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

Comments In AAAI-24

2312.03970 2023-12-08 cs.CV cs.AI cs.CE 85%

Improving Medical Report Generation with Adapter Tuning and Knowledge Enhancement in Vision-Language Foundation Models

Shibin Wu, Bang Yang, Zhiyu Ye, Haoqian Wang, Hairong Zheng, Tong Zhang

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

2311.07961 2023-11-15 cs.CL 85%

The ART of LLM Refinement: Ask, Refine, and Trust

Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ram Pasunuru, Mrinmaya Sachan, Jason Weston, Asli Celikyilmaz

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

2311.07689 2023-11-15 cs.CL 85%

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao

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

2311.01108 2023-11-03 cs.CL 85%

Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance

Song Wang, Zhen Tan, Ruocheng Guo, Jundong Li

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

Comments EMNLP Findings 2023

2311.01064 2023-11-03 cs.CV cs.LG 85%

Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images

Zalan Fabian, Zhongqi Miao, Chunyuan Li, Yuanhan Zhang, Ziwei Liu, Andrés Hernández, Andrés Montes-Rojas, Rafael Escucha, Laura Siabatto, Andrés Link, Pablo Arbeláez, Rahul Dodhia, Juan Lavista Ferres

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

Comments 18 pages, 9 figures

2310.15326 2023-10-25 cs.CL 85%

Specialist or Generalist? Instruction Tuning for Specific NLP Tasks

Chufan Shi, Yixuan Su, Cheng Yang, Yujiu Yang, Deng Cai

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 EMNLP 2023

2310.13226 2023-10-23 cs.CL 85%

Enhancing Zero-Shot Crypto Sentiment with Fine-tuned Language Model and Prompt Engineering

Rahman S M Wahidur, Ishmam Tashdeed, Manjit Kaur, Heung-No-Lee

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

2310.13127 2023-10-23 cs.CL 85%

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

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

Comments Accepted to EMNLP 2023 Findings. Work was done before July 2023

2310.08523 2023-10-13 cs.CL 85%

LLM-augmented Preference Learning from Natural Language

Inwon Kang, Sikai Ruan, Tyler Ho, Jui-Chien Lin, Farhad Mohsin, Oshani Seneviratne, Lirong Xia

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

2310.00653 2023-10-03 cs.CV cs.AI 85%

Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants

Tianyu Yu, Jinyi Hu, Yuan Yao, Haoye Zhang, Yue Zhao, Chongyi Wang, Shan Wang, Yinxv Pan, Jiao Xue, Dahai Li, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun

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

2309.14568 2023-09-27 cs.CL 85%

Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew

Shaltiel Shmidman, Avi Shmidman, Amir David Nissan Cohen, Moshe Koppel

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

2306.10723 2023-09-20 cs.CL cs.DB cs.LO 85%

Fine-tuning Large Enterprise Language Models via Ontological Reasoning

Teodoro Baldazzi, Luigi Bellomarini, Stefano Ceri, Andrea Colombo, Andrea Gentili, Emanuel Sallinger

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

Comments Accepted at RuleML 2023

2308.16753 2023-09-01 cs.IR cs.AI 85%

Context Aware Query Rewriting for Text Rankers using LLM

Abhijit Anand, Venktesh V, Vinay Setty, Avishek Anand

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

2304.14454 2023-08-28 cs.CL 85%

PMC-LLaMA: Towards Building Open-source Language Models for Medicine

Chaoyi Wu, Weixiong Lin, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie

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

2307.05646 2023-07-13 cs.CL 85%

Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models

Dhruv Mullick, Bilal Ghanem, Alona Fyshe

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

Comments Work done up till December 2022

2301.13268 2023-02-14 cs.CL 85%

Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems

Sandesh Swamy, Narges Tabari, Chacha Chen, Rashmi Gangadharaiah

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

Comments Accepted at EACL 2023 main conference. (Camera-ready version)

2205.12673 2022-10-27 cs.CL 85%

InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning

Prakhar Gupta, Cathy Jiao, Yi-Ting Yeh, Shikib Mehri, Maxine Eskenazi, Jeffrey P. Bigham

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

Comments EMNLP 2022

2108.02340 2021-08-06 cs.CL 85%

Robust Transfer Learning with Pretrained Language Models through Adapters

Wenjuan Han, Bo Pang, Yingnian Wu

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

Comments Accepted to ACL 2021

2504.20605 2026-05-05 cs.CL cs.AI cs.DL cs.LG 85%

TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models

TF1-EN-3M：三百万合成道德寓言用于训练小型开放语言模型

Mihai Nadas, Laura Diosan, Andrei Piscoran, Andreea Tomescu

机构 * Babeș-Bolyai University（巴纳德-波耶亚大学）； KlusAI Labs（KlusAI实验室）

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

AI总结本文提出TF1-EN-3M数据集，包含三百万英文寓言，用于训练小型开放语言模型，展示通过指令微调模型生成高质量寓言的方法，验证了无需大模型即可实现大规模道德叙事的可能性。

Comments 18 pages, 6 tables, 1 figure. v2: revised evaluation with open-weight LLM judge panel, expanded citations

1. 指令微调 11653 篇

The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning

Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method

TransLLaMa: LLM-based Simultaneous Translation System

Code Llama: Open Foundation Models for Code

Towards Building the Federated GPT: Federated Instruction Tuning

Language Models are Better Bug Detector Through Code-Pair Classification

Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications

UMIE: Unified Multimodal Information Extraction with Instruction Tuning

Contextual Code Switching for Machine Translation using Language Models

Visual Instruction Tuning with Polite Flamingo

Improving Medical Report Generation with Adapter Tuning and Knowledge Enhancement in Vision-Language Foundation Models

The ART of LLM Refinement: Ask, Refine, and Trust

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance

Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images

Specialist or Generalist? Instruction Tuning for Specific NLP Tasks

Enhancing Zero-Shot Crypto Sentiment with Fine-tuned Language Model and Prompt Engineering

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

LLM-augmented Preference Learning from Natural Language

Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants

Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew

Fine-tuning Large Enterprise Language Models via Ontological Reasoning

Context Aware Query Rewriting for Text Rankers using LLM

PMC-LLaMA: Towards Building Open-source Language Models for Medicine

Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models

Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems

InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning

Robust Transfer Learning with Pretrained Language Models through Adapters

TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models