大模型推理能力

Misinforming LLMs: vulnerabilities, challenges and opportunities

Bo Zhou, Daniel Geißler, Paul Lukowicz

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

Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming

Phoebe J. Wang, Max Kreminski

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

Comments Accepted to Wordplay @ ACL 2024

Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction

Suma Bailis, Jane Friedhoff, Feiyang Chen

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

Comments 13 pages, 10 figures

Grounding Language about Belief in a Bayesian Theory-of-Mind

Lance Ying, Tan Zhi-Xuan, Lionel Wong, Vikash Mansinghka, Joshua Tenenbaum

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

Comments Published at CogSci 2024

Learning to Generate All Feasible Actions

Mirco Theile, Daniele Bernardini, Raphael Trumpp, Cristina Piazza, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli

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

LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation

Hongke Zhao, Songming Zheng, Likang Wu, Bowen Yu, Jing Wang

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

Composition Vision-Language Understanding via Segment and Depth Anything Model

Mingxiao Huo, Pengliang Ji, Haotian Lin, Junchen Liu, Yixiao Wang, Yijun Chen

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

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models

Linhai Zhang, Jialong Wu, Deyu Zhou, Guoqiang Xu

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

Comments Accepted by ACL2024(Findings)

SyntaxShap: Syntax-aware Explainability Method for Text Generation

Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady

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

Comments Accepted to ACL 2024

Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba

İlker Işık, Ebru Aydin Gol, Ramazan Gokberk Cinbis

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

Comments 20 pages, 15 figures

Faithful Path Language Modeling for Explainable Recommendation over Knowledge Graph

Giacomo Balloccu, Ludovico Boratto, Christian Cancedda, Gianni Fenu, Mirko Marras

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

Transformers in the Service of Description Logic-based Contexts

Angelos Poulis, Eleni Tsalapati, Manolis Koubarakis

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

Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps

Fuxiao Liu, Paiheng Xu, Zongxia Li, Yue Feng, Hyemi Song

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

Comments 10 pages, 5 figures

Exploiting Contextual Structure to Generate Useful Auxiliary Tasks

Benedict Quartey, Ankit Shah, George Konidaris

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

Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models

Zhuoqun Li, Hongyu Lin, Yaojie Lu, Hao Xiang, Xianpei Han, Le Sun

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

Comments Accepted by LREC-COLING 2024 as a short paper

Softened Symbol Grounding for Neuro-symbolic Systems

Zenan Li, Yuan Yao, Taolue Chen, Jingwei Xu, Chun Cao, Xiaoxing Ma, Jian Lü

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

Comments Published as a conference paper at ICLR 2023. Code is available at https://github.com/SoftWiser-group/Soften-NeSy-learning

RL-GPT: Integrating Reinforcement Learning and Code-as-policy

Shaoteng Liu, Haoqi Yuan, Minda Hu, Yanwei Li, Yukang Chen, Shu Liu, Zongqing Lu, Jiaya Jia

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

Improving Neural-based Classification with Logical Background Knowledge

Arthur Ledaguenel, Céline Hudelot, Mostepha Khouadjia

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

Comments 9 pages, 3 figures, submitted to IJCAI 2024

Combining Machine Learning and Ontology: A Systematic Literature Review

Sarah Ghidalia, Ouassila Labbani Narsis, Aurélie Bertaux, Christophe Nicolle

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

Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion

Ruilin Luo, Tianle Gu, Haoling Li, Junzhe Li, Zicheng Lin, Jiayi Li, Yujiu Yang

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

Comments 15 pages; typos corrected, references added

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks

Peter Graf, Patrick Emami

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

Enhancing Robustness in Biomedical NLI Models: A Probing Approach for Clinical Trials

Ata Mustafa

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

ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases

Quyet V. Do, Tianqing Fang, Shizhe Diao, Zhaowei Wang, Yangqiu Song

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

Comments Proceedings of EACL 2024

Optimisation in Neurosymbolic Learning Systems

Emile van Krieken

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

Comments PhD dissertation

The two-way knowledge interaction interface between humans and neural networks

Zhanliang He, Nuoye Xiong, Hongsheng Li, Peiyi Shen, Guangming Zhu, Liang Zhang

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

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Jae Sung Park, Jack Hessel, Khyathi Raghavi Chandu, Paul Pu Liang, Ximing Lu, Peter West, Youngjae Yu, Qiuyuan Huang, Jianfeng Gao, Ali Farhadi, Yejin Choi

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

Comments Neurips 2023

MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic

Damien Sileo, Antoine Lernould

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

Comments Accepted at EMNLP Findings 2023

Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach

Harman Singh, Poorva Garg, Mohit Gupta, Kevin Shah, Ashish Goswami, Satyam Modi, Arnab Kumar Mondal, Dinesh Khandelwal, Dinesh Garg, Parag Singla

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

Comments EMNLP 2023 (long paper, main conference)

Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with Deep Learning

Thomas Decker, Michael Lebacher, Volker Tresp

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

Comments 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Impact of time and note duration tokenizations on deep learning symbolic music modeling

Nathan Fradet, Nicolas Gutowski, Fabien Chhel, Jean-Pierre Briot

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

Comments ISMIR 2023