语言大模型 / LLM - arXivDaily 专题

2310.09573 2023-10-17 cs.CL 79%

Self-Detoxifying Language Models via Toxification Reversal

Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, Wenjie Li

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

Comments Accepted by EMNLP 2023 main conference

2309.13625 2023-09-26 cs.CV cs.AI 79%

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

Xin Li, Dongze Lian, Zhihe Lu, Jiawang Bai, Zhibo Chen, Xinchao Wang

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

Comments Accepted by NeurIPS 2023. The manuscript will be further revised based on the reviews

2309.11758 2023-09-22 cs.CV cs.LG 79%

SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model to OCTA Image Segmentation Tasks

Chengliang Wang, Xinrun Chen, Haojian Ning, Shiying Li

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

Comments ICASSP conference is in submission

2309.11510 2023-09-22 cs.IR cs.AI cs.CV 79%

When is a Foundation Model a Foundation Model

Saghir Alfasly, Peyman Nejat, Sobhan Hemati, Jibran Khan, Isaiah Lahr, Areej Alsaafin, Abubakr Shafique, Nneka Comfere, Dennis Murphree, Chady Meroueh, Saba Yasir, Aaron Mangold, Lisa Boardman, Vijay Shah, Joaquin J. Garcia, H. R. Tizhoosh

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

2309.07727 2023-09-15 cs.CL 79%

PerPLM: Personalized Fine-tuning of Pretrained Language Models via Writer-specific Intermediate Learning and Prompts

Daisuke Oba, Naoki Yoshinaga, Masashi Toyoda

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

Comments 11 pages

2309.00751 2023-09-06 cs.CL 79%

Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence

Daniel Scalena, Gabriele Sarti, Malvina Nissim, Elisabetta Fersini

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

Comments 4 pages

2308.11507 2023-08-28 cs.CV cs.CL 79%

Unsupervised Prototype Adapter for Vision-Language Models

Yi Zhang, Ce Zhang, Xueting Hu, Zhihai He

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

Comments Accepted by PRCV 2023

2210.04845 2023-08-22 cs.CV cs.AI 79%

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

Adrian Bulat, Ricardo Guerrero, Brais Martinez, Georgios Tzimiropoulos

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

Comments Accepted at ICCV 2023

2308.08625 2023-08-21 cs.CL 79%

BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition

Pavlova Vera, Mohammed Makhlouf

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

Journal ref https://aclanthology.org/2023.bionlp-1.31/

2211.16198 2023-08-16 cs.CV cs.CL cs.MM 79%

SuS-X: Training-Free Name-Only Transfer of Vision-Language Models

Vishaal Udandarao, Ankush Gupta, Samuel Albanie

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

Comments Accepted at ICCV2023

2307.10522 2023-07-25 cs.CL 79%

Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models

Somayeh Ghanbarzadeh, Yan Huang, Hamid Palangi, Radames Cruz Moreno, Hamed Khanpour

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

Journal ref ACL 2023

2307.09484 2023-07-24 q-bio.BM cs.CE cs.LG physics.chem-ph 79%

MolFM: A Multimodal Molecular Foundation Model

Yizhen Luo, Kai Yang, Massimo Hong, Xing Yi Liu, Zaiqing Nie

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

Comments 31 pages, 15 figures, and 15 tables

2306.17322 2023-07-03 cs.CL 79%

Citations as Queries: Source Attribution Using Language Models as Rerankers

Ryan Muther, David Smith

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

2306.03423 2023-06-16 cs.AI 79%

I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models

Max Reuter, William Schulze

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

Comments Submitted for review to KDD 2023 via the workshop "Foundations and Applications in Large-scale AI Models: Pre-training, Fine-tuning, and Prompt-based Learning"

2110.02802 2023-06-16 cs.CL 79%

Self-conditioning pre-trained language models

Xavier Suau, Luca Zappella, Nicholas Apostoloff

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

Comments 8 pages and supplementary material, accepted at ICML 2022

2210.06629 2023-06-13 cs.CL 79%

Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis

Siddharth Varia, Shuai Wang, Kishaloy Halder, Robert Vacareanu, Miguel Ballesteros, Yassine Benajiba, Neha Anna John, Rishita Anubhai, Smaranda Muresan, Dan Roth

专题命中指令微调：instruction tuning(title)；prompting(abstract)；分类 cs.CL

Comments Camera ready copy for WASSA at ACL 2023

2306.00458 2023-06-08 cs.CL 79%

Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity

Katharina Hämmerl, Alina Fastowski, Jindřich Libovický, Alexander Fraser

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

Comments To appear in ACL Findings 2023. Fixed a citation in this version

2306.02569 2023-06-06 cs.CL 79%

Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models

Fengzhu Zeng, Wei Gao

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

Comments Accepted as ACL 2023 Findings

2301.09318 2023-06-02 cs.CV cs.LG 79%

Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation

Johannes Jakubik, Michal Muszynski, Michael Vössing, Niklas Kühl, Thomas Brunschwiler

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

Comments Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2023)

2305.18725 2023-05-31 cs.CL cs.DB 79%

AdapterEM: Pre-trained Language Model Adaptation for Generalized Entity Matching using Adapter-tuning

John Bosco Mugeni, Steven Lynden, Toshiyuki Amagasa, Akiyoshi Matono

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

2305.16876 2023-05-29 cs.CL 79%

CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models

Aitor Ormazabal, Mikel Artetxe, Eneko Agirre

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

Comments This previously appeared as arXiv:2205.12213v2, which was submitted as new by mistake

2305.11383 2023-05-29 cs.AI 79%

Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning

Po-Nien Kung, Nanyun Peng

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

Comments Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2212.07937 2023-05-29 cs.CL 79%

Visually-augmented pretrained language models for NLP tasks without images

Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Qinyu Zhang, Ji-Rong Wen

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

Comments 16 pages, 2 figures

2212.10315 2023-05-26 cs.CL 79%

HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation

Hamish Ivison, Akshita Bhagia, Yizhong Wang, Hannaneh Hajishirzi, Matthew Peters

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

Comments ACL 2023

2305.12217 2023-05-23 cs.CL 79%

PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search

Mozhi Zhang, Hang Yan, Yaqian Zhou, Xipeng Qiu

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

Comments work in progress

2304.07849 2023-05-16 cs.CL 79%

ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human

Junfeng Tian, Hehong Chen, Guohai Xu, Ming Yan, Xing Gao, Jianhai Zhang, Chenliang Li, Jiayi Liu, Wenshen Xu, Haiyang Xu, Qi Qian, Wei Wang, Qinghao Ye, Jiejing Zhang, Ji Zhang, Fei Huang, Jingren Zhou

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

Comments 36 pages

2212.08853 2023-05-12 cs.CL 79%

HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation

Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

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

Comments Accepted by ACL 2023

2305.04547 2023-05-09 cs.CL 79%

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

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

Comments Accepted by Findings of ACL 2023

2305.03300 2023-05-08 cs.CL 79%

LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa

Rahul Mehta, Vasudeva Varma

专题命中指令微调：LLM(title,abstract)；分类 cs.CL

Comments Submitted to SemEval-2023, The 17th International Workshop on Semantic Evaluation

2203.08459 2023-04-26 cs.CL 79%

KinyaBERT: a Morphology-aware Kinyarwanda Language Model

Antoine Nzeyimana, Andre Niyongabo Rubungo

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

Comments ACL 2022

1. 指令微调 11667 篇

Self-Detoxifying Language Models via Toxification Reversal

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model to OCTA Image Segmentation Tasks

When is a Foundation Model a Foundation Model

PerPLM: Personalized Fine-tuning of Pretrained Language Models via Writer-specific Intermediate Learning and Prompts

Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence

Unsupervised Prototype Adapter for Vision-Language Models

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition

SuS-X: Training-Free Name-Only Transfer of Vision-Language Models

Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models

MolFM: A Multimodal Molecular Foundation Model

Citations as Queries: Source Attribution Using Language Models as Rerankers

I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models

Self-conditioning pre-trained language models

Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis

Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity

Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models

Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation

AdapterEM: Pre-trained Language Model Adaptation for Generalized Entity Matching using Adapter-tuning

CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models

Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning

Visually-augmented pretrained language models for NLP tasks without images

HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation

PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search

ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human

HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa

KinyaBERT: a Morphology-aware Kinyarwanda Language Model