语言大模型 / LLM - arXivDaily 专题

2304.14953 2023-06-07 cs.CL 70%

CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data

Michał Turski, Tomasz Stanisławek, Karol Kaczmarek, Paweł Dyda, Filip Graliński

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

Comments Accepted at ICDAR 2023

2211.08099 2023-06-07 cs.CL 70%

A Universal Discriminator for Zero-Shot Generalization

Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng, Zhilin Yang

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

Comments ACL 2023 main conference (Long paper)

2306.01942 2023-06-06 cs.CL cs.SD eess.AS 70%

Can Contextual Biasing Remain Effective with Whisper and GPT-2?

Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland

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

Comments To appear in Interspeech 2023

2305.17817 2023-05-30 cs.CL stat.AP 70%

Transfer Learning for Power Outage Detection Task with Limited Training Data

Olukunle Owolabi

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

2206.12131 2023-05-30 cs.CL 70%

MVP: Multi-task Supervised Pre-training for Natural Language Generation

Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

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

Comments Accepted by ACL 2023

2305.16581 2023-05-29 cs.CL 70%

An Investigation of Noise in Morphological Inflection

Adam Wiemerslage, Changbing Yang, Garrett Nicolai, Miikka Silfverberg, Katharina Kann

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

Comments ACL 2023 Findings

2305.11908 2023-05-23 cs.HC cs.LG q-bio.NC stat.ML 70%

Sequential Best-Arm Identification with Application to Brain-Computer Interface

Xin Zhou, Botao Hao, Jian Kang, Tor Lattimore, Lexin Li

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

2305.10610 2023-05-19 cs.CL 70%

Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting

Saeth Wannasuphoprasit, Yi Zhou, Danushka Bollegala

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

Comments 7 pages, 5 figures. To be published in the Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 9-14 July 2023, Toronto, Canada

2305.07969 2023-05-19 cs.CL 70%

GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

Yutian Chen, Hao Kang, Vivian Zhai, Liangze Li, Rita Singh, Bhiksha Raj

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

2305.06474 2023-05-12 cs.IR cs.LG 70%

Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction

Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, Derek Zhiyuan Cheng

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

2211.08316 2023-05-12 cs.CL 70%

FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery

Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

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

Comments ACL Findings 2023

2304.13559 2023-05-01 cs.DB cs.CL 70%

Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables

Matthias Urban, Carsten Binnig

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

2304.14334 2023-04-28 cs.AI 70%

ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT

Solomon Ubani, Suleyman Olcay Polat, Rodney Nielsen

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

2302.03896 2023-04-14 cs.CL 70%

EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance

Zhengqing Yuan, Huiwen Xue, Chao Zhang, Yongming Liu

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

Comments 22 pages, 4 figures

Journal ref Appl. Sci. 2023, 13, 4758

2304.03612 2023-04-10 cs.CL cs.CY cs.HC 70%

What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory

Ronald Fischer, Markus Luczak-Roesch, Johannes A Karl

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

Comments 26 pages, 4 Figures, 5 Tables

2304.00115 2023-04-04 cs.CL 70%

Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods

Aman Pathak, Zehao Yu, Daniel Paredes, Elio Paul Monsour, Andrea Ortiz Rocha, Juan P. Brito, Naykky Singh Ospina, Yonghui Wu

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

2303.01067 2023-03-28 physics.ed-ph cs.AI 70%

AI and the FCI: Can ChatGPT Project an Understanding of Introductory Physics?

Colin G. West

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

Comments Updated and expanded. 13 pages, 1 figure, 1 table

2303.05349 2023-03-10 stat.AP cs.CL cs.CY 70%

Seeing ChatGPT Through Students' Eyes: An Analysis of TikTok Data

Anna-Carolina Haensch, Sarah Ball, Markus Herklotz, Frauke Kreuter

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

2302.12369 2023-02-27 eess.AS cs.CL cs.SD 70%

Factual Consistency Oriented Speech Recognition

Naoyuki Kanda, Takuya Yoshioka, Yang Liu

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

Comments 5 pages, 1 figure, 3 tables

2302.06860 2023-02-17 cs.CL 70%

BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction

Cai Yang, Addie Woicik, Hoifung Poon, Sheng Wang

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

2302.05940 2023-02-14 cs.SD cs.AI eess.AS 70%

SemanticAC: Semantics-Assisted Framework for Audio Classification

Yicheng Xiao, Yue Ma, Shuyan Li, Hantao Zhou, Ran Liao, Xiu Li

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

2212.12510 2023-01-06 cs.CL 70%

MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning

Luke Gessler, Amir Zeldes

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

Comments Presented at MRL at EMNLP 2022 in Abu Dhabi. Code at https://github.com/lgessler/microbert and models at https://huggingface.co/lgessler

2210.14852 2022-12-02 cs.CL 70%

Causality Detection using Multiple Annotation Decisions

Quynh Anh Nguyen, Arka Mitra

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

2211.10808 2022-11-22 cs.CL 70%

Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization

David Adams, Gandharv Suri, Yllias Chali

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

2202.04824 2022-11-21 cs.CL 70%

AdaPrompt: Adaptive Model Training for Prompt-based NLP

Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, Yue Zhang

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

2204.08110 2022-11-18 cs.CL 70%

Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models

Terra Blevins, Luke Zettlemoyer

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

Comments EMNLP 2022; corrected typos in appendix tables

2211.03988 2022-11-11 cs.CL cs.IR 70%

Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps

Hiroki Iida, Naoaki Okazaki

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

Comments AACL-IJCNLP2022 Camera Ready

2210.16952 2022-11-07 cs.CL 70%

Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning

Roshanak Mirzaee, Parisa Kordjamshidi

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

Comments The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

2210.04873 2022-11-02 cs.CL 70%

CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation

Tanay Dixit, Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer

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

Comments Findings EMNLP 2022

2210.16859 2022-11-01 cs.LG hep-th stat.ML 70%

A Solvable Model of Neural Scaling Laws

Alexander Maloney, Daniel A. Roberts, James Sully

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

Comments 73 + 23 pages, 14 + 5 figures

1. 预训练与数据 12486 篇

CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data

A Universal Discriminator for Zero-Shot Generalization

Can Contextual Biasing Remain Effective with Whisper and GPT-2?

Transfer Learning for Power Outage Detection Task with Limited Training Data

MVP: Multi-task Supervised Pre-training for Natural Language Generation

An Investigation of Noise in Morphological Inflection

Sequential Best-Arm Identification with Application to Brain-Computer Interface

Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting

GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction

FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery

Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables

ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT

EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance

What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory

Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods

AI and the FCI: Can ChatGPT Project an Understanding of Introductory Physics?

Seeing ChatGPT Through Students' Eyes: An Analysis of TikTok Data

Factual Consistency Oriented Speech Recognition

BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction

SemanticAC: Semantics-Assisted Framework for Audio Classification

MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning

Causality Detection using Multiple Annotation Decisions

Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization

AdaPrompt: Adaptive Model Training for Prompt-based NLP

Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models

Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps

Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning

CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation

A Solvable Model of Neural Scaling Laws