语言大模型 / LLM - arXivDaily 专题

2206.01134 2023-01-16 cs.AI cs.CL cs.LG 67%

Language and Culture Internalisation for Human-Like Autotelic AI

Cédric Colas, Tristan Karch, Clément Moulin-Frier, Pierre-Yves Oudeyer

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Journal ref Nature Machine Intelligence 4, 1068-1076 (2022)

2208.08367 2022-12-27 cs.CL cs.AI cs.LG 67%

Ask Question First for Enhancing Lifelong Language Learning

Han Wang, Ruiliu Fu, Xuejun Zhang, Jun Zhou, Qingwei Zhao

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This paper has been accepted for publication at COLING 2022

2212.10555 2022-12-21 cs.CL cs.AI cs.LG 67%

PairReranker: Pairwise Reranking for Natural Language Generation

Dongfu Jiang, Bill Yuchen Lin, Xiang Ren

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments We will release our code and data at https://inklab.usc.edu/PairReranker

2212.01924 2022-12-06 cs.CL cs.AI cs.LG 67%

Cross-lingual Similarity of Multilingual Representations Revisited

Maksym Del, Mark Fishel

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at AACL 2022

Journal ref AACL-IJCNLP 2022 Volume 1 Long Papers

2203.13696 2022-11-24 cs.SD cs.AI cs.CL cs.LG cs.MM eess.AS 67%

Speech-enhanced and Noise-aware Networks for Robust Speech Recognition

Hung-Shin Lee, Pin-Yuan Chen, Yao-Fei Cheng, Yu Tsao, Hsin-Min Wang

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in ISCSLP 2022

2206.08853 2022-11-23 cs.LG cs.AI cs.CL cs.CV 67%

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Mandlekar, Yuncong Yang, Haoyi Zhu, Andrew Tang, De-An Huang, Yuke Zhu, Anima Anandkumar

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Outstanding Paper Award at NeurIPS 2022. Project website: https://minedojo.org

2211.11527 2022-11-22 cs.CL cs.AI cs.IR cs.LG 67%

TIER-A: Denoising Learning Framework for Information Extraction

Yongkang Li, Ming Zhang

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2205.06175 2022-11-14 cs.AI cs.CL cs.LG cs.RO 67%

A Generalist Agent

Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo, Alexander Novikov, Gabriel Barth-Maron, Mai Gimenez, Yury Sulsky, Jackie Kay, Jost Tobias Springenberg, Tom Eccles, Jake Bruce, Ali Razavi, Ashley Edwards, Nicolas Heess, Yutian Chen, Raia Hadsell, Oriol Vinyals, Mahyar Bordbar, Nando de Freitas

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published at TMLR, 42 pages

Journal ref Transactions on Machine Learning Research, 11/2022, https://openreview.net/forum?id=1ikK0kHjvj

2205.12685 2022-10-25 cs.CL cs.AI cs.LG 67%

Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations

Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, Taeuk Kim

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to EMNLP Long. Kang Min Yoo and Junyeob Kim contributed equally. Kang Min Yoo and Taeuk Kim are the corresponding authors

2210.10693 2022-10-20 cs.CL cs.AI cs.LG 67%

Robustness of Demonstration-based Learning Under Limited Data Scenario

Hongxin Zhang, Yanzhe Zhang, Ruiyi Zhang, Diyi Yang

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 14 pages, EMNLP 2022 Main Conference

2206.05836 2022-10-13 cs.CV cs.AI cs.CL cs.LG cs.MM 67%

GLIPv2: Unifying Localization and Vision-Language Understanding

Haotian Zhang, Pengchuan Zhang, Xiaowei Hu, Yen-Chun Chen, Liunian Harold Li, Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, Jianfeng Gao

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2022; updated with reviewers' comments addressed; Code is released at https://github.com/microsoft/GLIP

2210.03826 2022-10-11 cs.CL cs.AI cs.LG stat.ML 67%

An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation

Jwala Dhamala, Varun Kumar, Rahul Gupta, Kai-Wei Chang, Aram Galstyan

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at IEEE SLT 2022

2208.06957 2022-10-04 cs.CL cs.AI cs.LG 67%

Syntax-driven Data Augmentation for Named Entity Recognition

Arie Pratama Sutiono, Gus Hahn-Powell

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments submitted to Pattern-based Approaches to NLP in the Age of Deep Learning 2022 (Pan-DL 2022)

2206.02338 2022-10-04 cs.CV 67%

OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression

Wanhua Li, Xiaoke Huang, Zheng Zhu, Yansong Tang, Xiu Li, Jie Zhou, Jiwen Lu

专题命中其他LLM ：language model(abstract)；prompting(abstract)

Comments Accepted by NeurIPS2022. Code is available at https://github.com/xk-huang/OrdinalCLIP

2208.14613 2022-09-02 cs.SE 67%

How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot

Naser Al Madi

专题命中其他LLM ：large language model(abstract)；language model(abstract)

2208.09659 2022-08-23 cs.CL cs.AI cs.LG 67%

Trigger-free Event Detection via Derangement Reading Comprehension

Jiachen Zhao, Haiqin Yang

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2206.11993 2022-06-27 cs.CL cs.AI cs.LG 67%

A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages

Akhter Al Amin, Kazi Sinthia Kabir

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 5 pages, 1 figure, 1 table, IJCAI 2022 Workshop on Diversity in Artificial Intelligence

2109.00527 2022-06-08 cs.CL cs.AI cs.IR cs.LG 67%

Boosting Search Engines with Interactive Agents

Leonard Adolphs, Benjamin Boerschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher, Sascha Rothe, Pier Giuseppe Sessa, Lierni Sestorain Saralegui

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in Transactions on Machine Learning Research (06/2022)

2205.14217 2022-05-31 cs.CL cs.AI cs.LG 67%

Diffusion-LM Improves Controllable Text Generation

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2109.01226 2022-05-26 cs.CL cs.AI cs.IT cs.LG math.IT 67%

So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements

James A. Michaelov, Seana Coulson, Benjamin K. Bergen

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted

Journal ref IEEE Transactions on Cognitive and Developmental Systems (2022)

2205.05646 2022-05-12 cs.CL cs.AI cs.LG 67%

Aggregating Pairwise Semantic Differences for Few-Shot Claim Veracity Classification

Xia Zeng, Arkaitz Zubiaga

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2104.08815 2022-05-09 cs.CL cs.AI cs.LG 67%

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks

Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to NAACL 2022 Findings. Github: https://github.com/FedML-AI/FedNLP

2203.09813 2022-03-21 cs.CL cs.AI cs.LG 67%

Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators

Keenan Jones, Jason R. C. Nurse, Shujun Li

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 13 pages, 6 figures, 4 tables, Accepted for publication in the proceedings of the sixteenth International AAAI Conference on Web and Social Media (ICWSM-22)

2202.10787 2022-02-23 cs.CL cs.AI cs.CV cs.LG 67%

VU-BERT: A Unified framework for Visual Dialog

Tong Ye, Shijing Si, Jianzong Wang, Rui Wang, Ning Cheng, Jing Xiao

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 5 pages, 2 figures, accepted by 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)

1809.01272 2021-12-28 cs.CL cs.AI cs.LG 67%

Unsupervised Statistical Machine Translation

Mikel Artetxe, Gorka Labaka, Eneko Agirre

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2018

2111.06599 2021-11-15 cs.CL cs.AI cs.LG 67%

PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages

Mohsin Ali, Kandukuri Sai Teja, Sumanth Manduru, Parth Patwa, Amitava Das

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted as Student Abstract at AAAI 2022

2109.11171 2021-09-24 cs.CL cs.AI cs.LG 67%

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2021; 14 pages, 5 figures, 9 tables

2101.02359 2021-09-24 cs.CL cs.AI cs.LG 67%

Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English

Xiangyang Li, Yu Xia, Xiang Long, Zheng Li, Sujian Li

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 3rd solution of 'Constraint@AAAI2021 - COVID19 Fake News Detection in English'

Journal ref First International Workshop, CONSTRAINT 2021 co-located with AAAI 2021

2109.07401 2021-09-16 cs.CL cs.AI cs.IR cs.LG 67%

Matching with Transformers in MELT

Sven Hertling, Jan Portisch, Heiko Paulheim

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments accepted at the Ontology Matching Workshop at the International Semantic Web Conference (ISWC 2021)

2109.04672 2021-09-13 cs.CL cs.AI cs.LG 67%

Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model

Kuntal Kumar Pal, Chitta Baral

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 7 pages, 10 figures, 5 tables, Accepted in the Findings of EMNLP 2021

1. 其他LLM 12287 篇

Language and Culture Internalisation for Human-Like Autotelic AI

Ask Question First for Enhancing Lifelong Language Learning

PairReranker: Pairwise Reranking for Natural Language Generation

Cross-lingual Similarity of Multilingual Representations Revisited

Speech-enhanced and Noise-aware Networks for Robust Speech Recognition

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

TIER-A: Denoising Learning Framework for Information Extraction

A Generalist Agent

Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations

Robustness of Demonstration-based Learning Under Limited Data Scenario

GLIPv2: Unifying Localization and Vision-Language Understanding

An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation

Syntax-driven Data Augmentation for Named Entity Recognition

OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression

How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot

Trigger-free Event Detection via Derangement Reading Comprehension

A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages

Boosting Search Engines with Interactive Agents

Diffusion-LM Improves Controllable Text Generation

So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements

Aggregating Pairwise Semantic Differences for Few-Shot Claim Veracity Classification

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks

Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators

VU-BERT: A Unified framework for Visual Dialog

Unsupervised Statistical Machine Translation

PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation

Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English

Matching with Transformers in MELT

Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model