语言大模型 / LLM - arXivDaily 专题

2303.01081 2023-03-03 cs.CL cs.AI 62%

Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study

Mingxu Tao, Yansong Feng, Dongyan Zhao

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ICLR 2023. URL: https://openreview.net/forum?id=UazgYBMS9-W

2302.12903 2023-02-28 cs.CL cs.AI 62%

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

Xuansheng Wu, Zhiyi Zhao, Ninghao Liu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 8+2+1 pages, 3+2 figures

2302.11978 2023-02-24 cs.LG cs.CL 62%

Does Deep Learning Learn to Abstract? A Systematic Probing Framework

Shengnan An, Zeqi Lin, Bei Chen, Qiang Fu, Nanning Zheng, Jian-Guang Lou

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments ICLR 2023

2302.11940 2023-02-24 cs.LG cs.AI 62%

Uncertainty Guided Ensemble Self-Training for Semi-Supervised Global Field Reconstruction

Yunyang Zhang, Zhiqiang Gong, Xiaoyu Zhao, Wen Yao

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.AI、cs.LG

2301.13154 2023-02-16 cs.LG cs.CL cs.MM 62%

Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling

Hong-Yu Zhou, Yunxiang Fu, Zhicheng Zhang, Cheng Bian, Yizhou Yu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Camera ready atICLR 2023. Code and models are available at https://github.com/RL4M/KeAP

2210.03765 2023-02-16 cs.CL cs.AI 62%

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments EACL 2023

2301.13631 2023-02-06 cs.CL cs.AI 62%

TopoBERT: Plug and Play Toponym Recognition Module Harnessing Fine-tuned BERT

Bing Zhou, Lei Zou, Yingjie Hu, Yi Qiang, Daniel Goldberg

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 8 Pages, 6 figures

2208.08609 2023-02-03 cs.AI cs.FL cs.LG cs.SC 62%

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables

Adrien Benamira, Tristan Guérand, Thomas Peyrin, Trevor Yap, Bryan Hooi

专题命中知识编辑与模型理解：post-training(abstract)；分类 cs.AI、cs.LG

2212.10400 2022-12-21 cs.CL cs.AI 62%

Contrastive Learning Reduces Hallucination in Conversations

Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren, Maarten de Rijke, Zhaochun Ren

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by AAAI2023

2211.07636 2022-12-06 cs.CV cs.CL cs.LG 62%

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Yuxin Fang, Wen Wang, Binhui Xie, Quan Sun, Ledell Wu, Xinggang Wang, Tiejun Huang, Xinlong Wang, Yue Cao

专题命中知识编辑与模型理解：foundation model(abstract)；分类 cs.CL、cs.LG

Comments v2: (i) fix / update EVA IN-1K variants results. (ii) add / update EVA-CLIP results. (iii) add Appendix. (iv) release all the code and models at https://github.com/baaivision/EVA

2210.01425 2022-12-06 cs.CL cs.AI 62%

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

Lunyiu Nie, Jiuding Sun, Yanlin Wang, Lun Du, Lei Hou, Juanzi Li, Shi Han, Dongmei Zhang, Jidong Zhai

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments AAAI 2023 Main Track Long Paper

2212.00587 2022-12-02 cs.CL cs.AI 62%

Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers

Frederico Dias Souza, João Baptista de Oliveira e Souza Filho

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 14 pages, 6 figures. Published at Springer Neural Computing and Applications journal

Journal ref Neural Comput & Applic (2022)

2211.14402 2022-11-29 cs.CL cs.CY cs.LG 62%

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages

Aristides Milios, Parishad BehnamGhader

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to 2022 Trustworthy and Socially Responsible Machine Learning (TSRML 2022) Workshop at NeurIPS 2022

2211.12312 2022-11-23 cs.LG cs.AI 62%

Interpreting Neural Networks through the Polytope Lens

Sid Black, Lee Sharkey, Leo Grinsztajn, Eric Winsor, Dan Braun, Jacob Merizian, Kip Parker, Carlos Ramón Guevara, Beren Millidge, Gabriel Alfour, Connor Leahy

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI、cs.LG

Comments 22/11/22 initial upload

2211.11153 2022-11-22 cs.LG cs.CL cs.CV 62%

Unifying Vision-Language Representation Space with Single-tower Transformer

Jiho Jang, Chaerin Kong, Donghyeon Jeon, Seonhoon Kim, Nojun Kwak

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.CL、cs.LG

Comments AAAI 2023, 11 pages

2211.11041 2022-11-22 cs.CL cs.AI cs.IT math.IT 62%

Pragmatic Constraint on Distributional Semantics

Elizaveta Zhemchuzhina, Nikolai Filippov, Ivan P. Yamshchikov

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2202.08975 2022-11-18 cs.SE cs.CL cs.LG 62%

Probing Pretrained Models of Source Code

Sergey Troshin, Nadezhda Chirkova

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.CL、cs.LG

2211.03495 2022-11-08 cs.CL cs.LG 62%

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

Michael Hassid, Hao Peng, Daniel Rotem, Jungo Kasai, Ivan Montero, Noah A. Smith, Roy Schwartz

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Findings of EMNLP 2022

2211.02899 2022-11-08 cs.CL cs.AI 62%

Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing

Rui Yu, Yifeng Li, Wenpeng Lu, Longbing Cao

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2211.00321 2022-11-02 cs.LG cs.AI 62%

Improving Variational Autoencoders with Density Gap-based Regularization

Jianfei Zhang, Jun Bai, Chenghua Lin, Yanmeng Wang, Wenge Rong

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted to NeurIPS 2022

2210.13236 2022-10-25 cs.CL cs.AI 62%

Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation

Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina, Viktoria Knyazkova, Tatiana Shavrina

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to BlackBoxNLP, EMNLP 2022

2210.11034 2022-10-21 cs.CL cs.LG 62%

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

Hyunsoo Cho, Choonghyun Park, Jaewook Kang, Kang Min Yoo, Taeuk Kim, Sang-goo Lee

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments EMNLP Findings 2022

2210.06312 2022-10-13 cs.CL cs.AI 62%

Changing the Representation: Examining Language Representation for Neural Sign Language Production

Harry Walsh, Ben Saunders, Richard Bowden

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 8 pages, 4 figures, 5 tables, SLTAT 2022

2204.09179 2022-10-13 cs.CL cs.LG 62%

On the Representation Collapse of Sparse Mixture of Experts

Zewen Chi, Li Dong, Shaohan Huang, Damai Dai, Shuming Ma, Barun Patra, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2022

2210.01258 2022-10-05 cs.CL cs.AI 62%

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

Ke Shen, Mayank Kejriwal

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2209.09871 2022-09-21 cs.CL cs.LG 62%

emojiSpace: Spatial Representation of Emojis

Moeen Mostafavi, Mahsa Pahlavikhah Varnosfaderani, Fateme Nikseresht, Seyed Ahmad Mansouri

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments 5 pages, 5 tables

2207.09336 2022-07-20 cs.LG cs.AI cs.CV eess.IV stat.ML 62%

Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance

Shervin Ardeshir, Navid Azizan

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.AI、cs.LG

2207.04648 2022-07-12 cs.LG cs.CL 62%

Learning Large-scale Universal User Representation with Sparse Mixture of Experts

Caigao Jiang, Siqiao Xue, James Zhang, Lingyue Liu, Zhibo Zhu, Hongyan Hao

专题命中知识编辑与模型理解：foundation model(abstract)；分类 cs.CL、cs.LG

Comments Accepted by ICML 2022 Pre-training Workshop

Journal ref International Conference on Machine Learning (ICML), First Workshop of Pre-training, 2022

2112.08547 2022-07-12 cs.CL cs.IR cs.LG 62%

Learning Rich Representation of Keyphrases from Text

Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, Rajarshi Bhowmik

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

2206.03248 2022-06-28 cs.CY cs.CL cs.LG 62%

Rites de Passage: Elucidating Displacement to Emplacement of Refugees on Twitter

Aparup Khatua, Wolfgang Nejdl

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments This work has been accepted to appear at HT'22-33rd ACM Conference on Hypertext and Social Media

1. 知识编辑与模型理解 7583 篇

Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

Does Deep Learning Learn to Abstract? A Systematic Probing Framework

Uncertainty Guided Ensemble Self-Training for Semi-Supervised Global Field Reconstruction

Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

TopoBERT: Plug and Play Toponym Recognition Module Harnessing Fine-tuned BERT

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables

Contrastive Learning Reduces Hallucination in Conversations

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages

Interpreting Neural Networks through the Polytope Lens

Unifying Vision-Language Representation Space with Single-tower Transformer

Pragmatic Constraint on Distributional Semantics

Probing Pretrained Models of Source Code

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing

Improving Variational Autoencoders with Density Gap-based Regularization

Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

Changing the Representation: Examining Language Representation for Neural Sign Language Production

On the Representation Collapse of Sparse Mixture of Experts

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

emojiSpace: Spatial Representation of Emojis

Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance

Learning Large-scale Universal User Representation with Sparse Mixture of Experts

Learning Rich Representation of Keyphrases from Text

Rites de Passage: Elucidating Displacement to Emplacement of Refugees on Twitter