语言大模型 / LLM - arXivDaily 专题

2104.08161 2021-10-14 cs.CL 70%

Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema

Yanai Elazar, Hongming Zhang, Yoav Goldberg, Dan Roth

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

Comments Accepted to EMNLP 2021

2109.11321 2021-10-01 cs.CL 70%

Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?

Tobias Norlund, Lovisa Hagström, Richard Johansson

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

2104.07425 2021-09-13 cs.CL 70%

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi, Kentaro Inui

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

Comments Long paper accepted by EMNLP2021 main conference

2109.04448 2021-09-10 cs.CL cs.CV 70%

Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers

Stella Frank, Emanuele Bugliarello, Desmond Elliott

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

Comments EMNLP 2021

2104.07504 2021-08-23 cs.CL 70%

Natural Language Understanding with Privacy-Preserving BERT

Chen Qu, Weize Kong, Liu Yang, Mingyang Zhang, Michael Bendersky, Marc Najork

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

Comments Accepted to CIKM 2021

2108.01850 2021-08-05 cs.CL 70%

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov

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

2107.06483 2021-07-15 cs.CL 70%

From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text

Ishan Tarunesh, Syamantak Kumar, Preethi Jyothi

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

Comments In Proceedings of The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021)

2004.12006 2021-07-14 cs.CL 70%

Contextualized Representations Using Textual Encyclopedic Knowledge

Mandar Joshi, Kenton Lee, Yi Luan, Kristina Toutanova

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

Comments Added experiments comparing linkers

2106.01221 2021-06-03 cs.CL cs.CR 70%

Differential Privacy for Text Analytics via Natural Text Sanitization

Xiang Yue, Minxin Du, Tianhao Wang, Yaliang Li, Huan Sun, Sherman S. M. Chow

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

Comments ACL-ICJNLP'21 Findings; The first two authors contributed equally

2105.02584 2021-05-07 cs.CL 70%

TABBIE: Pretrained Representations of Tabular Data

Hiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer

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

2104.06678 2021-04-15 cs.CL 70%

Large-Scale Self- and Semi-Supervised Learning for Speech Translation

Changhan Wang, Anne Wu, Juan Pino, Alexei Baevski, Michael Auli, Alexis Conneau

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

2103.13942 2021-03-26 cs.CL 70%

Visual Grounding Strategies for Text-Only Natural Language Processing

Damien Sileo

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

Comments Accepted at LANTERN2021

2012.05426 2021-03-19 cs.CL 70%

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

Yangming Li, Lemao Liu, Shuming Shi

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

Comments Accepted as a conference paper at ICLR 2021

2012.15516 2021-03-09 cs.CL 70%

AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding

Wissam Antoun, Fady Baly, Hazem Hajj

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

2102.11278 2021-02-24 cs.CL 70%

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

Usama Khalid, Mirza Omer Beg, Muhammad Umair Arshad

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

Comments arXiv admin note: substantial text overlap with arXiv:2102.10958

2011.03443 2020-11-09 q-bio.BM cs.LG 70%

Is Transfer Learning Necessary for Protein Landscape Prediction?

Amir Shanehsazzadeh, David Belanger, David Dohan

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

2004.13278 2020-11-03 cs.CV cs.CL 70%

VD-BERT: A Unified Vision and Dialog Transformer with BERT

Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, Steven C. H. Hoi

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

Comments EMNLP 2020 (14 pages)

2010.02239 2020-10-07 cs.CL 70%

Acrostic Poem Generation

Rajat Agarwal, Katharina Kann

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

Comments EMNLP 2020

2009.04007 2020-09-10 cs.CL 70%

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov

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

Comments Published at AAAI 2019

2005.03375 2020-05-08 cs.CL 70%

2kenize: Tying Subword Sequences for Chinese Script Conversion

Pranav A, Isabelle Augenstein

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

Comments Accepted to ACL 2020

2005.01677 2020-05-05 cs.CL 70%

Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

Young Mo Kang, Yingbo Zhou

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

Comments 4 pages, 1 figure

2005.00633 2020-05-05 cs.CL 70%

From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers

Anne Lauscher, Vinit Ravishankar, Ivan Vulić, Goran Glavaš

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

1910.07181 2020-04-30 cs.CL 70%

BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance

Timo Schick, Hinrich Schütze

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

Comments Accepted at ACL2020

1910.07713 2019-10-18 cs.CL 70%

BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge

Jeff Da

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

Comments Accepted to EMNLP Commonsense (COIN)

1905.03072 2019-10-02 cs.CL cs.SD eess.AS 70%

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation

Christoph Lüscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney

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

Comments Proceedings of INTERSPEECH 2019

1906.02525 2019-06-07 cs.CL 70%

Cross-Lingual Training for Automatic Question Generation

Vishwajeet Kumar, Nitish Joshi, Arijit Mukherjee, Ganesh Ramakrishnan, Preethi Jyothi

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

Comments ACL 2019

1903.08855 2019-04-29 cs.CL 70%

Linguistic Knowledge and Transferability of Contextual Representations

Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. Smith

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

Comments 22 pages, 4 figures; to appear at NAACL 2019

1811.01088 2019-03-01 cs.CL 70%

Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks

Jason Phang, Thibault Févry, Samuel R. Bowman

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

1809.00717 2018-09-05 cs.CL 70%

NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification

Alexandra Chronopoulou, Aikaterini Margatina, Christos Baziotis, Alexandros Potamianos

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

2605.12449 2026-05-13 cs.CV 69%

LychSim: A Controllable and Interactive Simulation Framework for Vision Research

LychSim：一种可控且交互式的视觉研究仿真框架

Wufei Ma, Chloe Wang, Siyi Chen, Jiawei Peng, Patrick Li, Alan Yuille

机构 * Johns Hopkins University（约翰霍普金斯大学）

专题命中预训练与数据：LLM(abstract_cn,comments)；pretraining(abstract)

AI总结 LychSim基于Unreal Engine 5构建，提供简洁的Python API、生成多样化高保真环境的流程数据管道以及MCP协议集成，用于视觉研究中的可控仿真与闭环优化。

Comments 3D-LLM/VLA Workshop at CVPR 2026. Project page: https://lychsim.github.io/

1. 预训练与数据 12486 篇

Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema

Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers

Natural Language Understanding with Privacy-Preserving BERT

Controlled Text Generation as Continuous Optimization with Multiple Constraints

From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text

Contextualized Representations Using Textual Encyclopedic Knowledge

Differential Privacy for Text Analytics via Natural Text Sanitization

TABBIE: Pretrained Representations of Tabular Data

Large-Scale Self- and Semi-Supervised Learning for Speech Translation

Visual Grounding Strategies for Text-Only Natural Language Processing

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

Is Transfer Learning Necessary for Protein Landscape Prediction?

VD-BERT: A Unified Vision and Dialog Transformer with BERT

Acrostic Poem Generation

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

2kenize: Tying Subword Sequences for Chinese Script Conversion

Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers

BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance

BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation

Cross-Lingual Training for Automatic Question Generation

Linguistic Knowledge and Transferability of Contextual Representations

Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks

NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification

LychSim: A Controllable and Interactive Simulation Framework for Vision Research