大模型推理能力

How Do In-Context Examples Affect Compositional Generalization?

Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, Dongmei Zhang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments ACL 2023 main conference, long paper

HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer

Yubin Kim, Dong Won Lee, Paul Pu Liang, Sharifa Algohwinem, Cynthia Breazeal, Hae Won Park

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding

Chenchi Zhang, Jun Xiao, Lei Chen, Jian Shao, Long Chen

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation

Xin-Ye Li, Jiang-Tian Xue, Zheng Xie, Ming Li

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 13 pages, 5 figures

Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans

John J. Nay

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Northwestern Journal of Technology and Intellectual Property, Volume 20, Issue 3, 2023

Qualitative Analysis of a Graph Transformer Approach to Addressing Hate Speech: Adapting to Dynamically Changing Content

Liam Hebert, Hong Yi Chen, Robin Cohen, Lukasz Golab

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted at AAAI 2023 AI for Social Good

Boosting Theory-of-Mind Performance in Large Language Models via Prompting

Shima Rahimi Moghaddam, Christopher J. Honey

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 27 pages, 4 main figures, 2 supplementary figures

Comparing NARS and Reinforcement Learning: An Analysis of ONA and $Q$-Learning Algorithms

Ali Beikmohammadi, Sindri Magnússon

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted in the 16th AGI Conference (AGI-23), Stockholm, Sweden, June 16 - June 19, 2023. arXiv admin note: text overlap with arXiv:2212.12517

Opportunities and Challenges in Neural Dialog Tutoring

Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments EACL 2023 (main conference, camera-ready)

Evaluating self-attention interpretability through human-grounded experimental protocol

Milan Bhan, Nina Achache, Victor Legrand, Annabelle Blangero, Nicolas Chesneau

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 11 pages, 7 figures

FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering

Qichen Ye, Bowen Cao, Nuo Chen, Weiyuan Xu, Yuexian Zou

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted in AAAI 2023, oral

Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes

Oren Sultan, Dafna Shahaf

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP 2022 main conference (long paper)

Chatbots as Problem Solvers: Playing Twenty Questions with Role Reversals

David Noever, Forrest McKee

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Cansu Sancaktar, Sebastian Blaes, Georg Martius

专题命中 复杂问题求解 ：planning(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2022 camera-ready version

Detect Only What You Specify : Object Detection with Linguistic Target

Moyuru Yamada

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Can Transformers Reason in Fragments of Natural Language?

Viktor Schlegel, Kamen V. Pavlov, Ian Pratt-Hartmann

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP 2022

Towards Language-driven Scientific AI

José Manuel Gómez-Pérez

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

MoCoDA: Model-based Counterfactual Data Augmentation

Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda

Learning by Distilling Context

Charlie Snell, Dan Klein, Ruiqi Zhong

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Explainable AI for clinical and remote health applications: a survey on tabular and time series data

Flavio Di Martino, Franca Delmastro

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

Asahi Ushio, Luis Espinosa-Anke, Steven Schockaert, Jose Camacho-Collados

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted by ACL 2021 main conference

Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries

Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Wu, Yuxiao Dong, Jie Tang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments kgTransformer; Accepted to KDD 2022

SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space

Liu Yang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments This submission has been withdrawn by arXiv administrators due to an unresolvable authorship dispute

Benchmarking the Spectrum of Agent Capabilities

Danijar Hafner

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Published at ICLR 2022. Website: https://danijar.com/crafter

Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts

Shane Storks, Qiaozi Gao, Aishwarya Reganti, Govind Thattai

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to CLeaR Workshop @ AAAI 2022

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long

专题命中 复杂问题求解 ：planning(abstract)；分类 cs.AI、cs.LG

Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration

Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments To appear at the 36th AAAI Conference on Artificial Intelligence (AAAI-22)

Causal policy ranking

Daniel McNamee, Hana Chockler

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments preprint; 6 pages. arXiv admin note: substantial text overlap with arXiv:2008.13607

GNN is a Counter? Revisiting GNN for Question Answering

Kuan Wang, Yuyu Zhang, Diyi Yang, Le Song, Tao Qin

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings

Peter Jansen, Kelly Smith, Dan Moreno, Huitzilin Ortiz

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP 2021