大模型推理能力

IDE-Net: Interactive Driving Event and Pattern Extraction from Human Data

Xiaosong Jia, Liting Sun, Masayoshi Tomizuka, Wei Zhan

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

Deriving Commonsense Inference Tasks from Interactive Fictions

Mo Yu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell

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

TaxiNLI: Taking a Ride up the NLU Hill

Pratik Joshi, Somak Aditya, Aalok Sathe, Monojit Choudhury

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

Comments 15 pages, 9 figures, 4 tables. Accepted at CoNLL 2020

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Peifeng Wang, Nanyun Peng, Filip Ilievski, Pedro Szekely, Xiang Ren

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

Comments 12 pages, 4 figures. Accepted to EMNLP'20 Findings

Vulnerabilities of Connectionist AI Applications: Evaluation and Defence

Christian Berghoff, Matthias Neu, Arndt von Twickel

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

Comments 20 pages, 8 figures, 1 table

TabFact: A Large-scale Dataset for Table-based Fact Verification

Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, William Yang Wang

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

Comments Accepted to ICLR 2020, 17 pages, 15 figures. Main paper has 9 pages

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel

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

Comments To Appear at ACL 2020

Commonsense Evidence Generation and Injection in Reading Comprehension

Ye Liu, Tao Yang, Zeyu You, Wei Fan, Philip S. Yu

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

Comments Accepted by SIGDIAL 2020

The Sensitivity of Language Models and Humans to Winograd Schema Perturbations

Mostafa Abdou, Vinit Ravishankar, Maria Barrett, Yonatan Belinkov, Desmond Elliott, Anders Søgaard

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

Comments ACL 2020

Learning to Complement Humans

Bryan Wilder, Eric Horvitz, Ece Kamar

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

Comments Accepted at IJCAI 2020

FreeLB: Enhanced Adversarial Training for Natural Language Understanding

Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, Jingjing Liu

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

Comments Adding results with ALBERT

Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games

Macheng Shen, Jonathan P. How

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

Improving Neural Story Generation by Targeted Common Sense Grounding

Huanru Henry Mao, Bodhisattwa Prasad Majumder, Julian McAuley, Garrison W. Cottrell

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

Conditional Self-Attention for Query-based Summarization

Yujia Xie, Tianyi Zhou, Yi Mao, Weizhu Chen

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

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

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

Comments Accepted by ICLR 2020

Relational Mimic for Visual Adversarial Imitation Learning

Lionel Blondé, Yichuan Charlie Tang, Jian Zhang, Russ Webb

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

Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks

Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

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

Scenarios and Recommendations for Ethical Interpretive AI

John Licato, Zaid Marji, Sophia Abraham

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

Comments To appear in the Proceedings of the Human-Centered AI: Trustworthiness of AI Models & Data (HAI) track at AAAI Fall Symposium, DC, November 7-9, 2019

Fusion of Detected Objects in Text for Visual Question Answering

Chris Alberti, Jeffrey Ling, Michael Collins, David Reitter

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

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models

Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann

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

DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs

Yi-Lin Tuan, Yun-Nung Chen, Hung-yi Lee

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

Comments Accepted to EMNLP 2019

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman

Chao Gao, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

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

Comments AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2019

CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense

Michael Chen, Mike D'Arcy, Alisa Liu, Jared Fernandez, Doug Downey

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

Comments 8 pages, Appeared in RepEval 2019

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

Shuangjia Zheng, Jiahua Rao, Zhongyue Zhang, Jun Xu, Yuedong Yang

专题命中 推理评测 ：planning(abstract)；分类 cs.CL、cs.LG

A Deep Reinforcement Learning Approach for Global Routing

Haiguang Liao, Wentai Zhang, Xuliang Dong, Barnabas Poczos, Kenji Shimada, Levent Burak Kara

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

Comments Preprint submitted to ASME JMD

Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition

Chao Gao, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor

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

Comments 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making

Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning

Qi Wu, Peng Wang, Chunhua Shen, Ian Reid, Anton van den Hengel

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

PinpointQA: A Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos

PinpointQA: 一个用于室内视频中微小物体中心空间理解的数据集和基准

Zhiyu Zhou, Peilin Liu, Ruoxuan Zhang, Luyang Zhang, Cheng Zhang, Hongxia Xie, Wen-Huang Cheng

机构 * Jilin University（吉林大学） ； National Taiwan University（国立台湾大学） 纠错

专题命中 推理评测 ：reasoning(abstract,comments)；分类 cs.AI

AI总结 本文提出PinpointQA数据集，用于评估多模态大语言模型在室内视频中对微小物体空间定位的精准理解能力，通过四个递进任务验证模型性能，并展示其作为诊断基准和训练数据集的效果。

Comments Accepted at the ECCV 2026 Workshop on Embodied Multimodal Reasoning in Physical Environments (EMR)

Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents

Mini-BEHAVIOR-Gran：揭示指令粒度对语言引导的具身智能体的影响

Sukai Huang, Chenyuan Zhang, Fucai Ke, Zhixi Cai, Gholamreza Haffari, Lizhen Qu, Hamid Rezatofighi

机构 * Faculty of Information Technology, Monash University（信息技术学院，莫纳什大学） 纠错

专题命中 推理评测 ：planning(abstract,comments)；分类 cs.AI

AI总结 本文提出Mini-BEHAVIOR-Gran基准，通过多级指令变体研究指令粒度对具身智能体性能的影响，发现粒度与性能呈非单调U型关系，粗粒度性能反弹与浅层 grounding 有关。

Comments 23 pages, Keywords: Language Grounding, Language Granularity, Instruction Following Agent, Width-based Planning Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond Research Area Keywords: vision language navigation, multimodality, neurosymbolic approaches

Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation

观察者，而非玩家：通过游戏观察模拟大语言模型中的理论心理论

Jerry Wang, Ting Yiu Liu

机构 * Department of Management Information Systems, National ChengChi University（管理信息系，国立中正大学） 纠错

专题命中 推理评测 ：reasoning(abstract,comments)；分类 cs.AI

AI总结 通过游戏观察模拟大语言模型中的理论心理论，评估其在顺序行为中的推理能力。

Comments Accepted at NeurIPS Workshop on Foundations of Reasoning in Language Models and Workshop on Bridging Language, Agent, and World Model