大模型推理能力 - arXivDaily 专题

2304.05351 2023-05-01 cs.CL cs.LG q-fin.ST 62%

The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges

Qianqian Xie, Weiguang Han, Yanzhao Lai, Min Peng, Jimin Huang

专题命中其他推理：chain-of-thought(abstract)；分类 cs.CL、cs.LG

Comments 13 pages

2212.08330 2023-05-01 cs.LG cs.CL cs.CV cs.NE 62%

Convolution-enhanced Evolving Attention Networks

Yujing Wang, Yaming Yang, Zhuo Li, Jiangang Bai, Mingliang Zhang, Xiangtai Li, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted by IEEE T-PAMI. Extension of the previous work (arXiv:2102.12895). arXiv admin note: text overlap with arXiv:2102.12895

2304.09979 2023-04-21 cs.LG cs.AI 62%

Beyond Transformers for Function Learning

Simon Segert, Jonathan Cohen

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

2302.10866 2023-04-21 cs.LG cs.CL 62%

Hyena Hierarchy: Towards Larger Convolutional Language Models

Michael Poli, Stefano Massaroli, Eric Nguyen, Daniel Y. Fu, Tri Dao, Stephen Baccus, Yoshua Bengio, Stefano Ermon, Christopher Ré

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Additional details

2304.06588 2023-04-14 cs.CL cs.AI cs.SI 62%

ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning

Petter Törnberg

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, 3 figures

2303.12669 2023-03-23 cs.CV cs.AI cs.LG 62%

An Extended Study of Human-like Behavior under Adversarial Training

Paul Gavrikov, Janis Keuper, Margret Keuper

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 6 pages, accepted at the CVPR 2023 Workshop "The 3rd Workshop of Adversarial Machine Learning on Computer Vision: Art of Robustness"

2303.10138 2023-03-20 cs.LG cs.AI 62%

Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data

Carlos Gemmell, Jeffrey Dalton

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

2210.07228 2023-03-17 cs.CL cs.LG 62%

Language Model Decoding as Likelihood-Utility Alignment

Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kıcıman, Boi Faltings, Robert West

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted at EACL (Findings) 2023

2303.08033 2023-03-15 cs.CL cs.AI 62%

Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code

Jaromir Savelka, Arav Agarwal, Christopher Bogart, Majd Sakr

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 12 pages

2303.02995 2023-03-07 cs.CV cs.CL cs.LG 62%

HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

Shijie Geng, Jianbo Yuan, Yu Tian, Yuxiao Chen, Yongfeng Zhang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted at ICLR 2023

2302.06967 2023-02-15 cs.AI cs.LG 62%

Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings

Luis Galárraga

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

Journal ref Full paper at the Symposium on Intelligent Data Analysis (IDA) 2023

2210.01963 2023-02-10 cs.CL cs.AI 62%

COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models

Kanishka Misra, Julia Taylor Rayz, Allyson Ettinger

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments EACL 2023 Camera Ready version. Code can be found at https://github.com/kanishkamisra/comps

2301.13852 2023-02-01 cs.CL cs.LG 62%

ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text

Sandra Mitrović, Davide Andreoletti, Omran Ayoub

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 11 pages, 8 figures, 2 tables

2301.07060 2023-01-19 cs.LG cs.AI cs.CY econ.GN q-fin.CP q-fin.EC 62%

Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance

Dangxing Chen, Luyao Zhang

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

2301.05334 2023-01-16 cs.LG cs.AI cs.MA 62%

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

Matteo Gallici, Mario Martin, Ivan Masmitja

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at AAMAS 2023. Code at https://github.com/mttga/pymarl_transformers

2212.08821 2022-12-20 cs.AI cs.LG 62%

Context-dependent Explainability and Contestability for Trustworthy Medical Artificial Intelligence: Misclassification Identification of Morbidity Recognition Models in Preterm Infants

Isil Guzey, Ozlem Ucar, Nukhet Aladag Ciftdemir, Betul Acunas

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 27 pages, 5 figures

2212.04348 2022-12-09 cs.CL cs.AI 62%

Implicit causality in GPT-2: a case study

Hien Huynh, Tomas O. Lentz, Emiel van Miltenburg

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, unpublished manuscript

2207.06881 2022-12-09 cs.CL cs.LG 62%

Recurrent Memory Transformer

Aydar Bulatov, Yuri Kuratov, Mikhail S. Burtsev

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

2210.07128 2022-12-07 cs.CL cs.LG 62%

Language Models of Code are Few-Shot Commonsense Learners

Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, Graham Neubig

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2022

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

专题命中其他推理：CoT(abstract)；分类 cs.CL、cs.AI

Comments This paper has been accepted by AAAI2023

2211.14343 2022-11-29 cs.AI cs.IT cs.LG cs.NI math.IT 62%

Less Data, More Knowledge: Building Next Generation Semantic Communication Networks

Christina Chaccour, Walid Saad, Merouane Debbah, Zhu Han, H. Vincent Poor

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

2211.13515 2022-11-28 cs.CL cs.AI 62%

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering

Yueqing Sun, Yu Zhang, Le Qi, Qi Shi

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Findings of EMNLP2022

2205.11169 2022-11-23 cs.CV cs.AI cs.CL 62%

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Yuan Yao, Qianyu Chen, Ao Zhang, Wei Ji, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted by EMNLP 2022

2210.03078 2022-10-25 cs.CL cs.AI 62%

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering

Jiacheng Liu, Skyler Hallinan, Ximing Lu, Pengfei He, Sean Welleck, Hannaneh Hajishirzi, Yejin Choi

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2022 main conference

2210.02928 2022-10-21 cs.CL cs.AI cs.CV 62%

MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text

Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, William W. Cohen

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP 2022 main conference

2210.06376 2022-10-13 cs.CL cs.AI 62%

Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary

Daniel Loureiro, Alípio Mário Jorge

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

2112.13428 2022-09-14 cs.CL cs.AI 62%

ArT: All-round Thinker for Unsupervised Commonsense Question-Answering

Jiawei Wang, Hai Zhao

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted by COLING 2022

2206.12094 2022-08-16 cs.CL cs.AI 62%

Unified BERT for Few-shot Natural Language Understanding

Junyu Lu, Ping Yang, Ruyi Gan, Jing Yang, Jiaxing Zhang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

2208.01769 2022-08-04 cs.MA cs.AI cs.LG 62%

Deep Reinforcement Learning for Multi-Agent Interaction

Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht

专题命中其他推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Published in AI Communications Special Issue on Multi-Agent Systems Research in the UK

2201.02662 2022-07-12 cs.CL cs.AI 62%

Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow

Maarten Sap, Anna Jafarpour, Yejin Choi, Noah A. Smith, James W. Pennebaker, Eric Horvitz

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Equal contribution from Sap and Jafarpour; in review; version 2

1. 其他推理 5813 篇

The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges

Convolution-enhanced Evolving Attention Networks

Beyond Transformers for Function Learning

Hyena Hierarchy: Towards Larger Convolutional Language Models

ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning

An Extended Study of Human-like Behavior under Adversarial Training

Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data

Language Model Decoding as Likelihood-Utility Alignment

Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code

HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings

COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models

ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text

Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

Context-dependent Explainability and Contestability for Trustworthy Medical Artificial Intelligence: Misclassification Identification of Morbidity Recognition Models in Preterm Infants

Implicit causality in GPT-2: a case study

Recurrent Memory Transformer

Language Models of Code are Few-Shot Commonsense Learners

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

Less Data, More Knowledge: Building Next Generation Semantic Communication Networks

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering

MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text

Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary

ArT: All-round Thinker for Unsupervised Commonsense Question-Answering

Unified BERT for Few-shot Natural Language Understanding

Deep Reinforcement Learning for Multi-Agent Interaction

Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow