语言大模型 / LLM - arXivDaily 专题

2302.12128 2023-02-24 cs.CL 57%

On the Generalization Ability of Retrieval-Enhanced Transformers

Tobias Norlund, Ehsan Doostmohammadi, Richard Johansson, Marco Kuhlmann

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2210.03588 2023-02-14 cs.CL 57%

Understanding Transformer Memorization Recall Through Idioms

Adi Haviv, Ido Cohen, Jacob Gidron, Roei Schuster, Yoav Goldberg, Mor Geva

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2302.03754 2023-02-09 cs.CL 57%

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

Suyu Ge, Chenyan Xiong, Corby Rosset, Arnold Overwijk, Jiawei Han, Paul Bennett

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2301.06736 2023-01-18 cs.CL 57%

Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

Kavya Manohar, A. R. Jayan, Rajeev Rajan

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2209.14338 2022-10-27 cs.CL 57%

Who is GPT-3? An Exploration of Personality, Values and Demographics

Marilù Miotto, Nicola Rossberg, Bennett Kleinberg

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments EMNLP 2022 NLP+CSS workshop

2205.04275 2022-06-07 cs.IR cs.CL 57%

Long Document Re-ranking with Modular Re-ranker

Luyu Gao, Jamie Callan

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments SIGIR 22

2110.02488 2022-06-03 cs.CL 57%

ABC: Attention with Bounded-memory Control

Hao Peng, Jungo Kasai, Nikolaos Pappas, Dani Yogatama, Zhaofeng Wu, Lingpeng Kong, Roy Schwartz, Noah A. Smith

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2205.12594 2022-05-26 cs.SD cs.LG eess.AS 57%

Heterogeneous Reservoir Computing Models for Persian Speech Recognition

Zohreh Ansari, Farzin Pourhoseini, Fatemeh Hadaeghi

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Comments This paper was accepted for oral presentation in IEEE WCCI 2022 + IJCNN 2022, special session on Reservoir Computing: algorithms, implementations and applications

2204.13061 2022-05-25 cs.LG cs.NE q-bio.NC 57%

Can deep learning match the efficiency of human visual long-term memory in storing object details?

A. Emin Orhan

专题命中长上下文与记忆：pretraining(abstract)；分类 cs.LG

Comments v3: mostly stylistic changes, no changes in main content

2112.07210 2022-05-05 cs.CL 57%

Simple Local Attentions Remain Competitive for Long-Context Tasks

Wenhan Xiong, Barlas Oğuz, Anchit Gupta, Xilun Chen, Diana Liskovich, Omer Levy, Wen-tau Yih, Yashar Mehdad

专题命中长上下文与记忆：pretraining(abstract)；分类 cs.CL

Comments NAACL 2022 Main Conference

2110.10150 2022-04-15 cs.CL 57%

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

Yusen Zhang, Ansong Ni, Ziming Mao, Chen Henry Wu, Chenguang Zhu, Budhaditya Deb, Ahmed H. Awadallah, Dragomir Radev, Rui Zhang

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments ACL 2022

2109.00301 2022-03-28 cs.CL 57%

$\infty$-former: Infinite Memory Transformer

Pedro Henrique Martins, Zita Marinho, André F. T. Martins

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments ACL 2022

2203.07522 2022-03-16 cs.CL 57%

Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering

Man Luo, Kazuma Hashimoto, Semih Yavuz, Zhiwei Liu, Chitta Baral, Yingbo Zhou

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2203.05081 2022-03-11 cs.CV cs.CL 57%

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

Fawaz Sammani, Tanmoy Mukherjee, Nikos Deligiannis

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments Accepted to CVPR 2022

2110.04744 2022-02-28 cs.LG math.DS stat.ML 57%

Long Expressive Memory for Sequence Modeling

T. Konstantin Rusch, Siddhartha Mishra, N. Benjamin Erichson, Michael W. Mahoney

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Comments ICLR 2022

1907.04352 2022-02-22 cs.SD cs.LG eess.AS 57%

Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls

Nicholas Meade, Nicholas Barreyre, Scott C. Lowe, Sageev Oore

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Journal ref International Conference on Computational Creativity, 2019

2106.08968 2021-12-08 cs.LG 57%

Optimized ensemble deep learning framework for scalable forecasting of dynamics containing extreme events

Arnob Ray, Tanujit Chakraborty, Dibakar Ghosh

专题命中长上下文与记忆：prompting(abstract)；分类 cs.LG

Comments 14 pages, 8 figures, any comments are welcome

2101.03289 2021-10-18 cs.CL 57%

Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing

Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, Thien Huu Nguyen

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments Camera-ready version for EACL 2021 Demo

2110.02204 2021-10-07 cs.CL 57%

Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy

Yi Zhou, Danushka Bollegala

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments Accepted to PACLIC 35

2109.11500 2021-09-24 cs.CR cs.LG 57%

LSTM Hyper-Parameter Selection for Malware Detection: Interaction Effects and Hierarchical Selection Approach

Mohit Sewak, Sanjay K. Sahay, Hemant Rathore

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Journal ref 2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1-9

2109.09075 2021-09-21 cs.CL 57%

Adversarial Training with Contrastive Learning in NLP

Daniela N. Rim, DongNyeong Heo, Heeyoul Choi

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2109.08780 2021-09-21 cs.LG cs.SE 57%

Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy

Colin B. Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Comments EMNLP 2021 camera ready

2104.10662 2021-09-15 cs.CL cs.SI 57%

COVID-19 sentiment analysis via deep learning during the rise of novel cases

Rohitash Chandra, Aswin Krishna

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Journal ref PLoS One, 2021

2109.05772 2021-09-14 cs.CL 57%

Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages

Antonis Maronikolakis, Philipp Dufter, Hinrich Schütze

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2021 Findings

2109.01078 2021-09-03 cs.CL 57%

Skim-Attention: Learning to Focus via Document Layout

Laura Nguyen, Thomas Scialom, Jacopo Staiano, Benjamin Piwowarski

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments 15 pages, 6 figures, to be published in EMNLP 2021 Findings

2108.06279 2021-08-20 cs.IR cs.CL 57%

On Single and Multiple Representations in Dense Passage Retrieval

Craig Macdonald, Nicola Tonellotto, Iadh Ounis

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

Comments Published at the 11th Italian Information Retrieval Workshop (IIR 2021)

2106.14342 2021-06-29 cs.LG stat.ML 57%

Stabilizing Equilibrium Models by Jacobian Regularization

Shaojie Bai, Vladlen Koltun, J. Zico Kolter

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

Comments ICML 2021 Short Oral

2106.13322 2021-06-28 cs.AI 57%

Dr. Watson type Artificial Intellect (AI) Systems

Saveli Goldberg, Stanislav Belyaev, Vladimir Sluchak

专题命中长上下文与记忆：prompting(abstract)；分类 cs.AI

Comments 24 pages,13 figures

2106.06738 2021-06-15 cs.CL 57%

A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data

Jinghui Lu, Maeve Henchion, Ivan Bacher, Brian Mac Namee

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL

2102.11174 2021-06-10 cs.LG 57%

Linear Transformers Are Secretly Fast Weight Programmers

Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber

专题命中长上下文与记忆：language model(abstract)；分类 cs.LG

1. 长上下文与记忆 4789 篇

On the Generalization Ability of Retrieval-Enhanced Transformers

Understanding Transformer Memorization Recall Through Idioms

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

Who is GPT-3? An Exploration of Personality, Values and Demographics

Long Document Re-ranking with Modular Re-ranker

ABC: Attention with Bounded-memory Control

Heterogeneous Reservoir Computing Models for Persian Speech Recognition

Can deep learning match the efficiency of human visual long-term memory in storing object details?

Simple Local Attentions Remain Competitive for Long-Context Tasks

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

$\infty$-former: Infinite Memory Transformer

Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

Long Expressive Memory for Sequence Modeling

Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls

Optimized ensemble deep learning framework for scalable forecasting of dynamics containing extreme events

Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing

Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy

LSTM Hyper-Parameter Selection for Malware Detection: Interaction Effects and Hierarchical Selection Approach

Adversarial Training with Contrastive Learning in NLP

Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy

COVID-19 sentiment analysis via deep learning during the rise of novel cases

Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages

Skim-Attention: Learning to Focus via Document Layout

On Single and Multiple Representations in Dense Passage Retrieval

Stabilizing Equilibrium Models by Jacobian Regularization

Dr. Watson type Artificial Intellect (AI) Systems

A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data

Linear Transformers Are Secretly Fast Weight Programmers