语言大模型 / LLM - arXivDaily 专题

2301.07608 2023-01-19 cs.LG cs.AI cs.NE 62%

Human-Timescale Adaptation in an Open-Ended Task Space

Adaptive Agent Team, Jakob Bauer, Kate Baumli, Satinder Baveja, Feryal Behbahani, Avishkar Bhoopchand, Nathalie Bradley-Schmieg, Michael Chang, Natalie Clay, Adrian Collister, Vibhavari Dasagi, Lucy Gonzalez, Karol Gregor, Edward Hughes, Sheleem Kashem, Maria Loks-Thompson, Hannah Openshaw, Jack Parker-Holder, Shreya Pathak, Nicolas Perez-Nieves, Nemanja Rakicevic, Tim Rocktäschel, Yannick Schroecker, Jakub Sygnowski, Karl Tuyls, Sarah York, Alexander Zacherl, Lei Zhang

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

2301.06602 2023-01-18 cs.CL cs.LG 62%

TEDB System Description to a Shared Task on Euphemism Detection 2022

Peratham Wiriyathammabhum

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

Comments EMNLP workshop 2022 SharedTask report. FigLang 2022

2301.02807 2023-01-10 cs.CL cs.AI cs.IR 62%

RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm

Hamid Gharagozlou, Javad Mohammadzadeh, Azam Bastanfard, Saeed Shiry Ghidary

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

Comments 21 pages

Journal ref Computational Intelligence and Neuroscience (2022)

2212.14206 2023-01-02 cs.CL cs.IR cs.LG 62%

Maximizing Use-Case Specificity through Precision Model Tuning

Pranjali Awasthi, David Recio-Mitter, Yosuke Kyle Sugi

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

Comments 9 pages, 4 figures

2212.07127 2022-12-23 cs.CL cs.LG 62%

Towards mapping the contemporary art world with ArtLM: an art-specific NLP model

Qinkai Chen, Mohamed El-Mennaoui, Antoine Fosset, Amine Rebei, Haoyang Cao, Philine Bouscasse, Christy Eóin O'Beirne, Sasha Shevchenko, Mathieu Rosenbaum

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

2106.09553 2022-12-15 cs.LG cs.CL q-bio.BM 62%

Large-Scale Chemical Language Representations Capture Molecular Structure and Properties

Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, Inkit Padhi, Youssef Mroueh, Payel Das

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

Comments NMI 2022

2211.15848 2022-12-05 cs.IR cs.AI cs.CL 62%

ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information

Arnold Overwijk, Chenyan Xiong, Xiao Liu, Cameron VandenBerg, Jamie Callan

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

2208.07670 2022-12-05 cs.CL cs.AI 62%

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin, Zhongyuan Wang, Songlin Hu

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

Comments This paper has been accepted by AAAI2023

2211.16164 2022-11-30 cs.CL cs.AI 62%

Few-shot Query-Focused Summarization with Prefix-Merging

Ruifeng Yuan, Zili Wang, Ziqiang Cao, Wenjie Li

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

Comments Accepted by EMNLP2022

2205.13189 2022-11-29 cs.LG cs.AI cs.CV 62%

AI for Porosity and Permeability Prediction from Geologic Core X-Ray Micro-Tomography

Zangir Iklassov, Dmitrii Medvedev, Otabek Nazarov, Shakhboz Razzokov

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

2211.12142 2022-11-23 cs.CL cs.AI 62%

Coreference Resolution through a seq2seq Transition-Based System

Bernd Bohnet, Chris Alberti, Michael Collins

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

2211.08406 2022-11-18 q-bio.BM cs.AI cs.LG 62%

Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design

Kaiyuan Gao, Lijun Wu, Jinhua Zhu, Tianbo Peng, Yingce Xia, Liang He, Shufang Xie, Tao Qin, Haiguang Liu, Kun He, Tie-Yan Liu

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

2211.06778 2022-11-15 cs.CL cs.AI 62%

Textual Data Augmentation for Patient Outcomes Prediction

Qiuhao Lu, Dejing Dou, Thien Huu Nguyen

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

Comments BIBM 2021

2211.05826 2022-11-14 cs.CL cs.AI 62%

The CRINGE Loss: Learning what language not to model

Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

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

2204.11817 2022-11-07 cs.CL cs.AI 62%

Translation between Molecules and Natural Language

Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, Heng Ji

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

Comments Accepted at EMNLP 2022. Data and code can be found on [Github](https://github.com/blender-nlp/MolT5)

2211.01978 2022-11-04 q-bio.BM cs.AI cs.LG 62%

PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction

Yuancheng Sun, Yimeng Chen, Weizhi Ma, Wenhao Huang, Kang Liu, Zhiming Ma, Wei-Ying Ma, Yanyan Lan

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

Comments 9 pages. Published in CIKM 2022

2209.06640 2022-11-02 cs.LG cs.AI 62%

Revisiting Neural Scaling Laws in Language and Vision

Ibrahim Alabdulmohsin, Behnam Neyshabur, Xiaohua Zhai

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

Journal ref Neural Information Processing Systems (NeurIPS), 2022

2210.16169 2022-10-31 cs.LG cs.AI cs.IT math.IT math.OC 62%

LOFT: Finding Lottery Tickets through Filter-wise Training

Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis

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

2210.15859 2022-10-31 cs.CL cs.LG 62%

You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM

Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, Mohit Iyyer

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

2210.14724 2022-10-27 cs.CL cs.AI 62%

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao

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

Comments Accepted by UEIoT2022, The 3rd International Workshop on Ubiquitous Electric Internet of Things

2210.13938 2022-10-26 cs.CL cs.AI cs.IT math.IT 62%

Dual Mechanism Priming Effects in Hindi Word Order

Sidharth Ranjan, Marten van Schijndel, Sumeet Agarwal, Rajakrishnan Rajkumar

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

Comments Accepted to AACL 2022

2205.08836 2022-10-24 cs.CV cs.AI cs.LG cs.NE 62%

Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization

Christoph Linse, Thomas Martinetz

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

Comments 11 pages, 3 figures, 4 tables

2210.02914 2022-10-19 cs.CL cs.AI 62%

Generative Entity Typing with Curriculum Learning

Siyu Yuan, Deqing Yang, Jiaqing Liang, Zhixu Li, Jinxi Liu, Jingyue Huang, Yanghua Xiao

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

Comments Accepted to EMNLP 2022

2109.03564 2022-10-19 cs.CL cs.AI 62%

NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction

Yi Sun, Yu Zheng, Chao Hao, Hangping Qiu

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

Comments Published at COLING2022, long paper

2210.07652 2022-10-17 cs.CL cs.AI 62%

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

Yejin Bang, Tiezheng Yu, Andrea Madotto, Zhaojiang Lin, Mona Diab, Pascale Fung

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

2210.07277 2022-10-17 cs.LG cs.AI cs.CV 62%

The Hidden Uniform Cluster Prior in Self-Supervised Learning

Mahmoud Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Nicolas Ballas

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

2210.05613 2022-10-12 cs.CL cs.AI 62%

Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents

Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros

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

2210.04864 2022-10-11 cs.CV cs.AI cs.CL 62%

Transformer-based Localization from Embodied Dialog with Large-scale Pre-training

Meera Hahn, James M. Rehg

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

Journal ref International Joint Conference on Natural Language Processing (2022)

2204.10716 2022-10-04 cs.LG cs.CL 62%

Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding

Leibo Liu, Oscar Perez-Concha, Anthony Nguyen, Vicki Bennett, Louisa Jorm

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

Journal ref Journal of Biomedical Informatics 133 (2022) 104161

2209.12678 2022-09-27 cs.CL cs.LG cs.NE 62%

Flexible Job Classification with Zero-Shot Learning

Thom Lake

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

Comments To be published in RecSys in HR'22

1. 预训练与数据 12534 篇

Human-Timescale Adaptation in an Open-Ended Task Space

TEDB System Description to a Shared Task on Euphemism Detection 2022

RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm

Maximizing Use-Case Specificity through Precision Model Tuning

Towards mapping the contemporary art world with ArtLM: an art-specific NLP model

Large-Scale Chemical Language Representations Capture Molecular Structure and Properties

ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

Few-shot Query-Focused Summarization with Prefix-Merging

AI for Porosity and Permeability Prediction from Geologic Core X-Ray Micro-Tomography

Coreference Resolution through a seq2seq Transition-Based System

Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design

Textual Data Augmentation for Patient Outcomes Prediction

The CRINGE Loss: Learning what language not to model

Translation between Molecules and Natural Language

PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction

Revisiting Neural Scaling Laws in Language and Vision

LOFT: Finding Lottery Tickets through Filter-wise Training

You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

Dual Mechanism Priming Effects in Hindi Word Order

Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization

Generative Entity Typing with Curriculum Learning

NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

The Hidden Uniform Cluster Prior in Self-Supervised Learning

Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents

Transformer-based Localization from Embodied Dialog with Large-scale Pre-training

Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding

Flexible Job Classification with Zero-Shot Learning