语言大模型 / LLM - arXivDaily 专题

2401.00575 2024-01-02 cs.CL 70%

Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets

Payam Karisani

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

Comments ACL Findings 2023

2401.00435 2024-01-02 cs.CV cs.AI 70%

Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition

Hanbo Cheng, Chenyu Liu, Pengfei Hu, Zhenrong Zhang, Jiefeng Ma, Jun Du

专题命中预训练与数据：language model(abstract)；SLM(abstract)；分类 cs.AI

2401.00424 2024-01-02 cs.CL 70%

SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection

Shijue Huang, Libo Qin, Bingbing Wang, Geng Tu, Ruifeng Xu

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by ICASSP 2024

2401.00210 2024-01-02 cs.CL cs.CY 70%

The Problem of Alignment

Tsvetelina Hristova, Liam Magee, Karen Soldatic

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 23 pages, 1 figure

2310.05450 2024-01-02 cs.CL 70%

Empower Nested Boolean Logic via Self-Supervised Curriculum Learning

Hongqiu Wu, Linfeng Liu, Hai Zhao, Min Zhang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by EMNLP2023

2304.14318 2023-12-27 cs.CL 70%

q2d: Turning Questions into Dialogs to Teach Models How to Search

Yonatan Bitton, Shlomi Cohen-Ganor, Ido Hakimi, Yoad Lewenberg, Roee Aharoni, Enav Weinreb

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2023. Website: https://question2dialog.github.io/

2312.11785 2023-12-20 cs.CL 70%

Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs

Zhangdie Yuan, Andreas Vlachos

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2101.00153 2023-12-20 cs.CL 70%

Graphmax for Text Generation

Liu Bin, Yin Guosheng

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Journal ref Journal of Artificial Intelligence Research, vol. 78, pp.823-848, Nov. 2023

2307.16456 2023-12-19 cs.CL 70%

Camoscio: an Italian Instruction-tuned LLaMA

Andrea Santilli, Emanuele Rodolà

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Published at CLiC-it 2023

2312.06147 2023-12-12 cs.CL cs.IR 70%

"What's important here?": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces

Faria Huq, Jeffrey P. Bigham, Nikolas Martelaro

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to NeurIPS 2023 R0-FoMo Workshop

2312.05464 2023-12-12 cs.CV cs.LG 70%

Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation

Atoosa Chegini, Soheil Feizi

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.LG

2311.17218 2023-11-30 cs.CV cs.LG 70%

BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling

Yixuan Luo, Mengye Ren, Sai Qian Zhang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.LG

2311.14735 2023-11-28 q-fin.ST cs.LG 70%

Generative Machine Learning for Multivariate Equity Returns

Ruslan Tepelyan, Achintya Gopal

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 13 pages, 2-column format, presented at ICAIF'23

2311.12290 2023-11-22 cs.LG 70%

A Supervised Contrastive Learning Pretrain-Finetune Approach for Time Series

Trang H. Tran, Lam M. Nguyen, Kyongmin Yeo, Nam Nguyen, Roman Vaculin

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)；分类 cs.LG

2310.19909 2023-11-21 cs.CV cs.LG 70%

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.LG

Comments Accepted to NeurIPS 2023

2311.10266 2023-11-20 cs.CL 70%

Diagnosing and Debiasing Corpus-Based Political Bias and Insults in GPT2

Ambri Ma, Arnav Kumar, Brett Zeligson

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 9 pages

2305.16651 2023-11-15 cs.CL 70%

TADA: Task-Agnostic Dialect Adapters for English

Will Held, Caleb Ziems, Diyi Yang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 5 Pages; ACL Findings Paper 2023

2311.06364 2023-11-14 cs.CL 70%

Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach

Maxime Delmas, Magdalena Wysocka, André Freitas

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2311.04547 2023-11-09 cs.CL 70%

Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures

Julius Steuer, Marius Mosbach, Dietrich Klakow

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

2311.02265 2023-11-09 cs.CL 70%

Not all layers are equally as important: Every Layer Counts BERT

Lucas Georges Gabriel Charpentier, David Samuel

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

2311.02310 2023-11-07 cs.CL 70%

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles

Weiting Tan, Haoran Xu, Lingfeng Shen, Shuyue Stella Li, Kenton Murray, Philipp Koehn, Benjamin Van Durme, Yunmo Chen

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2311.01751 2023-11-06 cs.CL 70%

EmojiLM: Modeling the New Emoji Language

Letian Peng, Zilong Wang, Hang Liu, Zihan Wang, Jingbo Shang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

2310.12560 2023-11-06 cs.LG 70%

Fast Model Debias with Machine Unlearning

Ruizhe Chen, Jianfei Yang, Huimin Xiong, Jianhong Bai, Tianxiang Hu, Jin Hao, Yang Feng, Joey Tianyi Zhou, Jian Wu, Zuozhu Liu

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.LG

2311.01233 2023-11-03 cs.CV cs.AI 70%

Long Story Short: a Summarize-then-Search Method for Long Video Question Answering

Jiwan Chung, Youngjae Yu

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Published in BMVC 2023

2311.00953 2023-11-03 cs.CL 70%

Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation

Wanyu Du, Yangfeng Ji

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

2311.00926 2023-11-03 cs.RO cs.AI cs.CV 70%

M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place

Wentao Yuan, Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 12 pages, 8 figures, accepted by CoRL 2023

2304.05197 2023-11-02 cs.CL cs.CR 70%

Multi-step Jailbreaking Privacy Attacks on ChatGPT

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Findings of EMNLP 2023. Updated with results on open-source LLMs

2310.20158 2023-11-01 cs.CL 70%

GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval

Daman Arora, Anush Kini, Sayak Ray Chowdhury, Nagarajan Natarajan, Gaurav Sinha, Amit Sharma

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments preprint

2305.16289 2023-10-31 cs.CV cs.AI 70%

Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation

Lisa Dunlap, Alyssa Umino, Han Zhang, Jiezhi Yang, Joseph E. Gonzalez, Trevor Darrell

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.AI

Comments Update: replaced Planes dataset with Waterbirds & updated results after bug fix

2304.06939 2023-10-31 cs.CV cs.CL 70%

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

Wanrong Zhu, Jack Hessel, Anas Awadalla, Samir Yitzhak Gadre, Jesse Dodge, Alex Fang, Youngjae Yu, Ludwig Schmidt, William Yang Wang, Yejin Choi

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

Comments NeurIPS D&B 2023. Project homepage: https://github.com/allenai/mmc4

1. 预训练与数据 12486 篇

Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets

Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition

SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection

The Problem of Alignment

Empower Nested Boolean Logic via Self-Supervised Curriculum Learning

q2d: Turning Questions into Dialogs to Teach Models How to Search

Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs

Graphmax for Text Generation

Camoscio: an Italian Instruction-tuned LLaMA

"What's important here?": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces

Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation

BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling

Generative Machine Learning for Multivariate Equity Returns

A Supervised Contrastive Learning Pretrain-Finetune Approach for Time Series

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Diagnosing and Debiasing Corpus-Based Political Bias and Insults in GPT2

TADA: Task-Agnostic Dialect Adapters for English

Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach

Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures

Not all layers are equally as important: Every Layer Counts BERT

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles

EmojiLM: Modeling the New Emoji Language

Fast Model Debias with Machine Unlearning

Long Story Short: a Summarize-then-Search Method for Long Video Question Answering

Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation

M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place

Multi-step Jailbreaking Privacy Attacks on ChatGPT

GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval

Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text