语言大模型 / LLM - arXivDaily 专题

2102.00238 2022-02-04 cs.CL cs.LG 73%

ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models

Rutuja Taware, Shraddha Varat, Gaurav Salunke, Chaitanya Gawande, Geetanjali Kale, Rahul Khengare, Raviraj Joshi

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

2002.08131 2022-02-03 cs.CL cs.LG 73%

A Systematic Comparison of Architectures for Document-Level Sentiment Classification

Jeremy Barnes, Vinit Ravishankar, Lilja Øvrelid, Erik Velldal

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

Comments 5 pages, 2 figures

2110.02950 2021-12-21 cs.CL cs.CY cs.LG 73%

Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer

Wenda Xu, Michael Saxon, Misha Sra, William Yang Wang

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

Comments 12 pages, 8 tables, 3 figures. AAAI 2022 Conference Paper

2112.08616 2021-12-17 cs.CL cs.LG 73%

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Daniel Spokoyny, Ivan Lee, Zhao Jin, Taylor Berg-Kirkpatrick

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

Comments Preprint

2112.05587 2021-12-16 cs.CV cs.CL cs.LG 73%

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

Tianyi Liu, Zuxuan Wu, Wenhan Xiong, Jingjing Chen, Yu-Gang Jiang

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

2108.02446 2021-11-25 cs.CL cs.AI 73%

Finetuning Pretrained Transformers into Variational Autoencoders

Seongmin Park, Jihwa Lee

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

Comments Proceedings of the Second Workshop on Insights from Negative Results in NLP

2111.08137 2021-11-17 cs.CL cs.LG cs.SD eess.AS 73%

Joint Unsupervised and Supervised Training for Multilingual ASR

Junwen Bai, Bo Li, Yu Zhang, Ankur Bapna, Nikhil Siddhartha, Khe Chai Sim, Tara N. Sainath

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

2104.08758 2021-10-01 cs.CL cs.AI 73%

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, Matt Gardner

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

Comments EMNLP 2021 accepted paper camera ready version

2108.01624 2021-08-04 cs.LG cs.CL cs.CR 73%

Large-Scale Differentially Private BERT

Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, Pasin Manurangsi

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

Comments 12 pages, 6 figures

2107.12591 2021-07-28 cs.LG cs.AI 73%

Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning

Hoifung Poon, Hai Wang, Hunter Lang

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

Comments Book chapter. arXiv admin note: substantial text overlap with arXiv:2012.12474, arXiv:1808.08485, arXiv:2008.12878

2107.09931 2021-07-22 cs.CL cs.LG 73%

The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding

Archiki Prasad, Mohammad Ali Rehan, Shreya Pathak, Preethi Jyothi

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

2006.03659 2021-05-28 cs.CL cs.LG 73%

DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations

John Giorgi, Osvald Nitski, Bo Wang, Gary Bader

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

Comments ACL2021 Camera Ready V2

2004.07683 2021-03-30 cs.CL cs.LG 73%

Do sequence-to-sequence VAEs learn global features of sentences?

Tom Bosc, Pascal Vincent

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

Comments Camera-ready version, EMNLP2020

2008.09075 2021-03-26 cs.CL cs.AI 73%

Controlling Dialogue Generation with Semantic Exemplars

Prakhar Gupta, Jeffrey P. Bigham, Yulia Tsvetkov, Amy Pavel

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

Comments Accepted at NAACL 2021

2101.10649 2021-01-27 cs.CL cs.AI 73%

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

Hyunjin Choi, Judong Kim, Seongho Joe, Seungjai Min, Youngjune Gwon

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

Comments 6 pages, 4 figures, to be published in 25th International Conference on Pattern Recognition, ICPR 2020

2012.00363 2020-12-02 cs.CL cs.LG 73%

Modifying Memories in Transformer Models

Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix Yu, Sanjiv Kumar

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

2010.15065 2020-10-29 q-bio.BM cs.CL cs.LG 73%

Fixed-Length Protein Embeddings using Contextual Lenses

Amir Shanehsazzadeh, David Belanger, David Dohan

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

2010.01825 2020-10-06 cs.LG cs.CL stat.ML 73%

PMI-Masking: Principled masking of correlated spans

Yoav Levine, Barak Lenz, Opher Lieber, Omri Abend, Kevin Leyton-Brown, Moshe Tennenholtz, Yoav Shoham

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

2010.01057 2020-10-05 cs.CL cs.LG 73%

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention

Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto

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

Comments EMNLP 2020

2005.12766 2020-06-19 cs.CL cs.LG stat.ML 73%

CERT: Contrastive Self-supervised Learning for Language Understanding

Hongchao Fang, Sicheng Wang, Meng Zhou, Jiayuan Ding, Pengtao Xie

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

2004.13835 2020-04-30 cs.CL cs.AI 73%

A Tailored Pre-Training Model for Task-Oriented Dialog Generation

Jing Gu, Qingyang Wu, Chongruo Wu, Weiyan Shi, Zhou Yu

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

Comments 7 pages, 1 figure

2002.09599 2020-02-25 cs.CL cs.AI 73%

Training Question Answering Models From Synthetic Data

Raul Puri, Ryan Spring, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

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

2002.00750 2020-02-06 cs.CL cs.LG cs.SD eess.AS 73%

Joint Contextual Modeling for ASR Correction and Language Understanding

Yue Weng, Sai Sumanth Miryala, Chandra Khatri, Runze Wang, Huaixiu Zheng, Piero Molino, Mahdi Namazifar, Alexandros Papangelis, Hugh Williams, Franziska Bell, Gokhan Tur

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

Comments Accepted at IEEE ICASSP 2020

1904.06707 2019-12-05 cs.CL cs.LG 73%

Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking

Timo Schick, Hinrich Schütze

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

Comments To appear at AAAI 2020

1805.03294 2019-08-06 cs.CL cs.LG stat.ML 73%

Improved training of end-to-end attention models for speech recognition

Albert Zeyer, Kazuki Irie, Ralf Schlüter, Hermann Ney

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

Comments submitted to Interspeech 2018

1906.04329 2019-06-12 cs.CL cs.LG 73%

Federated Learning for Emoji Prediction in a Mobile Keyboard

Swaroop Ramaswamy, Rajiv Mathews, Kanishka Rao, Françoise Beaufays

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

1511.01432 2015-11-05 cs.LG cs.CL 73%

Semi-supervised Sequence Learning

Andrew M. Dai, Quoc V. Le

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

2603.20235 2026-03-24 cs.CY cs.AI cs.HC 72%

Writing literature reviews with AI: principles, hurdles and some lessons learned

用AI撰写文献综述：原则、障碍与一些经验教训

Saadi Lahlou, Annabelle Gouttebroze, Atrina Oraee, Julian Madera

机构 * London School of Economics and Political Science（伦敦政治经济学院）； Paris Institute for Advanced Study（巴黎高级研究学院）

专题命中预训练与数据：LLM(abstract,comments)；prompting(abstract)；分类 cs.AI

AI总结本文通过比较不同AI辅助程度下的文献综述，揭示了AI生成内容的偏见、主流化倾向及局限性，强调了在使用AI撰写综述时需注意的防范措施。

Comments 31 pages and 193 pages of Appendices, including 6 different versions of the literature review, and complete chat with the LLM

2511.13022 2025-11-18 cs.LG 72%

Learning Time-Scale Invariant Population-Level Neural Representations

Eshani Patel, Yisong Yue, Geeling Chau

机构 * Computing & Mathematical Sciences（计算与数学科学）； Computation & Neural Systems（计算与神经系统）； California Institute of Technology（加州理工学院）

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

Comments 10 pages, 5 figures, NeurIPS 2025 Foundation Models for the Brain and Body

2502.17664 2025-03-11 cs.CL 72%

Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages

Tsan Tsai Chan, Xin Tong, Thi Thu Uyen Hoang, Barbare Tepnadze, Wojciech Stempniak

机构 * Saarland University（萨尔大学）

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

Comments ISCA/ITG Workshop on Diversity in Large Speech and Language Models

1. 预训练与数据 12486 篇

ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models

A Systematic Comparison of Architectures for Document-Level Sentiment Classification

Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

Finetuning Pretrained Transformers into Variational Autoencoders

Joint Unsupervised and Supervised Training for Multilingual ASR

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Large-Scale Differentially Private BERT

Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning

The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding

DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations

Do sequence-to-sequence VAEs learn global features of sentences?

Controlling Dialogue Generation with Semantic Exemplars

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

Modifying Memories in Transformer Models

Fixed-Length Protein Embeddings using Contextual Lenses

PMI-Masking: Principled masking of correlated spans

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention

CERT: Contrastive Self-supervised Learning for Language Understanding

A Tailored Pre-Training Model for Task-Oriented Dialog Generation

Training Question Answering Models From Synthetic Data

Joint Contextual Modeling for ASR Correction and Language Understanding

Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking

Improved training of end-to-end attention models for speech recognition

Federated Learning for Emoji Prediction in a Mobile Keyboard

Semi-supervised Sequence Learning

Writing literature reviews with AI: principles, hurdles and some lessons learned

Learning Time-Scale Invariant Population-Level Neural Representations

Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages