大模型推理能力 - arXivDaily 专题

2307.13617 2023-07-27 cs.CL cs.AI 62%

GPT-3 Models are Few-Shot Financial Reasoners

Raul Salles de Padua, Imran Qureshi, Mustafa U. Karakaplan

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 15 pages, 8 figures

Journal ref CS & IT Conference Proceedings (2023), volume 13, number 12, pages 183-197

2307.07699 2023-07-18 cs.AI cs.CL cs.SC 62%

Leveraging Large Language Models to Generate Answer Set Programs

Adam Ishay, Zhun Yang, Joohyung Lee

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 17 pages, KR 2023

2307.04895 2023-07-12 cs.AI cs.LG 62%

Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer

Zhun Yang, Adam Ishay, Joohyung Lee

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 22 pages. The Eleventh International Conference on Learning Representations (ICLR 2023)

2306.11161 2023-06-21 cs.LG cs.AI 62%

Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research

Chace Ashcraft, Jennifer Sleeman, Caroline Tang, Jay Brett, Anand Gnanadesikan

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

2305.14825 2023-06-09 cs.CL cs.AI 62%

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Xiaojuan Tang, Zilong Zheng, Jiaqi Li, Fanxu Meng, Song-Chun Zhu, Yitao Liang, Muhan Zhang

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

2306.05058 2023-06-09 cs.LG cs.AI eess.SP 62%

Neuro-Symbolic Approaches for Context-Aware Human Activity Recognition

Luca Arrotta, Gabriele Civitarese, Claudio Bettini

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

2306.03902 2023-06-07 cs.CL cs.AI cs.LO q-bio.NC 62%

Utterance Classification with Logical Neural Network: Explainable AI for Mental Disorder Diagnosis

Yeldar Toleubay, Don Joven Agravante, Daiki Kimura, Baihan Lin, Djallel Bouneffouf, Michiaki Tatsubori

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments ACL 2023

2207.03777 2023-05-29 cs.CL cs.AI 62%

Hidden Schema Networks

Ramsés J. Sánchez, Lukas Conrads, Pascal Welke, Kostadin Cvejoski, César Ojeda

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments accepted at ACL 2023

2305.13917 2023-05-24 cs.CL cs.AI 62%

Generating Data for Symbolic Language with Large Language Models

Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu

专题命中逻辑推理：verifier(abstract)；分类 cs.CL、cs.AI

2305.08876 2023-05-18 cs.NE cs.AI cs.LG 62%

Neurosymbolic AI and its Taxonomy: a survey

Wandemberg Gibaut, Leonardo Pereira, Fabio Grassiotto, Alexandre Osorio, Eder Gadioli, Amparo Munoz, Sildolfo Gomes, Claudio dos Santos

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments submitted to ACM Computing Surveys

2304.07995 2023-04-18 cs.CL cs.AI 62%

From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning

Qian Liu, Fan Zhou, Zhengbao Jiang, Longxu Dou, Min Lin

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Work in Progress. The code is released at https://github.com/sail-sg/symbolic-instruction-tuning

2210.01162 2023-03-17 cs.RO cs.AI cs.FL cs.LG math.OC 62%

Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications

Mingyu Cai, Makai Mann, Zachary Serlin, Kevin Leahy, Cristian-Ioan Vasile

专题命中逻辑推理：planning(abstract)；分类 cs.AI、cs.LG

2110.03501 2023-03-15 stat.ML cs.CL cs.LG 62%

Pretrained Language Models are Symbolic Mathematics Solvers too!

Kimia Noorbakhsh, Modar Sulaiman, Mahdi Sharifi, Kallol Roy, Pooyan Jamshidi

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.LG

2303.05186 2023-03-10 cs.LG cs.AI cs.SE 62%

A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning

Juan Marcelo Parra-Ullauri, Chen Zhen, Antonio García-Domínguez, Nelly Bencomo, Changgang Zheng, Juan Boubeta-Puig, Guadalupe Ortiz, Shufan Yang

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

2203.04571 2023-03-06 cs.LG cs.AI cs.CV 62%

A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices

Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Updated version with additional NVSA end-to-end training, generalization experiments, and PGM experiments

2302.09458 2023-02-21 cs.CL cs.LG cs.LO 62%

Learning Language Representations with Logical Inductive Bias

Jianshu Chen

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Published as a conference paper at ICLR 2023

2103.02728 2023-02-08 cs.AI cs.CL cs.CY 62%

Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agents

Cosmin Badea, Gregory Artus

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Journal ref In: Bramer, M., Stahl, F. (eds) Artificial Intelligence XXXIX. SGAI-AI 2022. Lecture Notes in Computer Science(), vol 13652. Springer, Cham (2022)

2212.05254 2022-12-13 cs.CL cs.AI 62%

MAPS-KB: A Million-scale Probabilistic Simile Knowledge Base

Qianyu He, Xintao Wang, Jiaqing Liang, Yanghua Xiao

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to AAAI 2023

2210.16606 2022-11-01 cs.LG cs.AI cs.SC 62%

Neural Combinatorial Logic Circuit Synthesis from Input-Output Examples

Peter Belcak, Roger Wattenhofer

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to the 2nd Workshop on Math-AI (MATH-AI@NeurIPS'22). 10 pages, 1 figure

2210.05173 2022-10-12 cs.AI cs.LG 62%

On Explainability in AI-Solutions: A Cross-Domain Survey

Simon Daniel Duque Anton, Daniel Schneider, Hans Dieter Schotten

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Journal ref SAFECOMP 2022 Workshops (2022) 235-246

2209.00448 2022-09-02 cs.AI cs.CL 62%

Intelligent Traffic Monitoring with Hybrid AI

Ehsan Qasemi, Alessandro Oltramari

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments IJCAI Workshop on Artificial Intelligence for Autonomous Driving (AI4AD) 2022

2208.13518 2022-08-30 cs.AI cs.CL cs.CV cs.LO cs.SC 62%

LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems

Björn Deiseroth, Patrick Schramowski, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

2205.10768 2022-05-24 cs.LG cs.AI cs.IT math.IT 62%

Neuro-Symbolic Artificial Intelligence (AI) for Intent based Semantic Communication

Christo Kurisummoottil Thomas, Walid Saad

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

2205.00047 2022-05-03 cs.LG cs.CL cs.CR 62%

Logically Consistent Adversarial Attacks for Soft Theorem Provers

Alexander Gaskell, Yishu Miao, Lucia Specia, Francesca Toni

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments IJCAI-ECAI 2022

2203.05079 2022-03-11 cs.LG cs.AI 62%

SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning

Andrew Chester, Michael Dann, Fabio Zambetta, John Thangarajah

专题命中逻辑推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 8 figures, 3 tables

2203.04378 2022-03-10 cs.AI cs.LG 62%

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine

Charul Giri, Ole-Christoffer Granmo, Herke van Hoof, Christian D. Blakely

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

2202.06538 2022-02-15 cs.CL cs.AI 62%

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation

Dan Su, Peng Xu, Pascale Fung

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 4 pages, accepted by ICASSP2022

2010.03950 2022-01-19 cs.LG cs.AI 62%

Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Valenzano, Sheila A. McIlraith

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Journal ref Journal of Artificial Intelligence Research 73 (2022) 173-208

2012.13635 2021-12-24 cs.AI cs.LG 62%

Logic Tensor Networks

Samy Badreddine, Artur d'Avila Garcez, Luciano Serafini, Michael Spranger

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 68 pages, 28 figures, 6 tables

Journal ref Artificial Intelligence, Volume 303, February 2022, 103649

2112.00578 2021-12-02 cs.CL cs.LG 62%

Systematic Generalization with Edge Transformers

Leon Bergen, Timothy J. O'Donnell, Dzmitry Bahdanau

专题命中逻辑推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted as a conference paper at NeurIPS 2021

1. 逻辑推理 3024 篇

GPT-3 Models are Few-Shot Financial Reasoners

Leveraging Large Language Models to Generate Answer Set Programs

Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer

Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Neuro-Symbolic Approaches for Context-Aware Human Activity Recognition

Utterance Classification with Logical Neural Network: Explainable AI for Mental Disorder Diagnosis

Hidden Schema Networks

Generating Data for Symbolic Language with Large Language Models

Neurosymbolic AI and its Taxonomy: a survey

From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning

Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications

Pretrained Language Models are Symbolic Mathematics Solvers too!

A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning

A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices

Learning Language Representations with Logical Inductive Bias

Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agents

MAPS-KB: A Million-scale Probabilistic Simile Knowledge Base

Neural Combinatorial Logic Circuit Synthesis from Input-Output Examples

On Explainability in AI-Solutions: A Cross-Domain Survey

Intelligent Traffic Monitoring with Hybrid AI

LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems

Neuro-Symbolic Artificial Intelligence (AI) for Intent based Semantic Communication

Logically Consistent Adversarial Attacks for Soft Theorem Provers

SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation

Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

Logic Tensor Networks

Systematic Generalization with Edge Transformers