大模型推理能力 - arXivDaily 专题

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

2108.01843 2022-06-22 cs.LG cs.AI cs.MA 62%

Model-Based Opponent Modeling

Xiaopeng Yu, Jiechuan Jiang, Wanpeng Zhang, Haobin Jiang, Zongqing Lu

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

Comments 21 pages, 10 figures

2206.06007 2022-06-14 cs.AI cs.LG cs.RO 62%

Intrinsically motivated option learning: a comparative study of recent methods

Djordje Božić, Predrag Tadić, Mladen Nikolić

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

Comments Accepted for presentation at the 2021 29th Telecommunications Forum (TELFOR), Belgrade, Serbia

2206.03720 2022-06-09 cs.LG cs.CL 62%

Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction

Mateusz Jurewicz, Leon Derczynski

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

Comments Paper accepted for publication in the IJCAI-ECAI 2022 proceedings: https://www.ijcai.org/proceedings/

2112.06888 2022-05-30 cs.CL cs.CV cs.LG 62%

Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection

Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh

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

Journal ref Proceedings of the 1st International Workshop on Multimodal Understanding for the Web and Social Media, co-located with the Web Conference 2022 (WWW '22 Companion), April 25--29, 2022, Virtual Event, Lyon, France

2204.12632 2022-05-17 cs.CL cs.AI 62%

Testing the Ability of Language Models to Interpret Figurative Language

Emmy Liu, Chen Cui, Kenneth Zheng, Graham Neubig

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

Comments NAACL 2022

2205.05230 2022-05-12 cs.LG cs.AI 62%

Developing cooperative policies for multi-stage reinforcement learning tasks

Jordan Erskine, Chris Lehnert

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

Comments This paper supersedes the rejected paper "Developing cooperative policies for multi-stage tasks". arXiv admin note: substantial text overlap with arXiv:2007.00203

2112.08777 2022-05-09 cs.CL cs.AI 62%

Long Context Question Answering via Supervised Contrastive Learning

Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan

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

Comments accepted NAACL 2022, main conference

2205.01809 2022-05-06 cs.AI cs.CL 62%

Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

Marco Valentino, André Freitas

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

2202.08906 2022-05-03 cs.CL cs.LG 62%

ST-MoE: Designing Stable and Transferable Sparse Expert Models

Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, William Fedus

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

Comments 25 pages main text, 39 pages overall

2204.10200 2022-04-22 cs.SE cs.AI cs.CL cs.PL 62%

An Exploratory Study on Code Attention in BERT

Rishab Sharma, Fuxiang Chen, Fatemeh Fard, David Lo

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

Comments Accepted in ICPC 2022

2204.05210 2022-04-12 cs.CL cs.AI 62%

Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling

Nuo Chen, Linjun Shou, Ming Gong, Jian Pei, Daxin Jiang

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

Comments 15 pages

2203.15827 2022-03-31 cs.CL cs.LG 62%

LinkBERT: Pretraining Language Models with Document Links

Michihiro Yasunaga, Jure Leskovec, Percy Liang

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

Comments Published at ACL 2022. Code, data, and pretrained models are available at https://github.com/michiyasunaga/LinkBERT

2203.11211 2022-03-23 cs.LG cs.AI 62%

ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning

Jasmina Gajcin, Ivana Dusparic

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

Comments 18 pages, 4 tables, 4 figures

2203.10343 2022-03-22 cs.CL cs.AI 62%

Automatic Detection of Entity-Manipulated Text using Factual Knowledge

Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan

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

Comments Association for Computational Linguistics (ACL) 2022 camera-ready

2203.07559 2022-03-16 cs.CL cs.LG 62%

On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency

Seo Yeon Park, Cornelia Caragea

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

Comments Accepted at ACL 2022 main conference

2108.09241 2022-03-04 cs.CL cs.AI 62%

Open Relation Modeling: Learning to Define Relations between Entities

Jie Huang, Kevin Chen-Chuan Chang, Jinjun Xiong, Wen-mei Hwu

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

Comments Accepted to Findings of ACL 2022

2202.11768 2022-02-25 cs.AI cs.CL 62%

From Unstructured Text to Causal Knowledge Graphs: A Transformer-Based Approach

Scott Friedman, Ian Magnusson, Vasanth Sarathy, Sonja Schmer-Galunder

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

Comments arXiv admin note: substantial text overlap with arXiv:2108.13304

2201.09518 2022-01-25 cs.CL cs.AI 62%

Synthetic Books

Varvara Guljajeva

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

Comments 7 pages, 5 figures

Journal ref ARTECH 2021

2112.08616 2021-12-17 cs.CL cs.LG 62%

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Daniel Spokoyny, Ivan Lee, Zhao Jin, Taylor Berg-Kirkpatrick

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

Comments Preprint

2110.08322 2021-11-10 cs.LG cs.AI 62%

Robustness of different loss functions and their impact on networks learning capability

Vishal Rajput

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

2111.02603 2021-11-05 cs.CL cs.AI 62%

On Semantic Cognition, Inductive Generalization, and Language Models

Kanishka Misra

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

Comments Accepted at AAAI 2022 Doctoral Consortium

2110.08268 2021-10-19 cs.CY cs.AI cs.LG 62%

Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails

Kun Niu, Xipeng Cao, Yicong Yu

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

Comments AAAI 2021 Workshop on AI Education/TIPCE 2021

2104.12763 2021-10-13 cs.CV cs.CL cs.LG 62%

MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding

Aishwarya Kamath, Mannat Singh, Yann LeCun, Gabriel Synnaeve, Ishan Misra, Nicolas Carion

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

2104.08401 2021-10-08 cs.CL cs.AI 62%

Enriching a Model's Notion of Belief using a Persistent Memory

Nora Kassner, Oyvind Tafjord, Hinrich Schutze, Peter Clark

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

Comments This is an old and now obsolete draft. See arXiv:2109.14723 ("BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief") for the final paper

2107.13074 2021-07-29 cs.HC cs.AI cs.LG 62%

Toward AI Assistants That Let Designers Design

Sebastiaan De Peuter, Antti Oulasvirta, Samuel Kaski

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

Comments 9 pages, 3 figures, submitted to IEEE Computer magazine

1. 其他推理 5878 篇

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

Model-Based Opponent Modeling

Intrinsically motivated option learning: a comparative study of recent methods

Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction

Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection

Testing the Ability of Language Models to Interpret Figurative Language

Developing cooperative policies for multi-stage reinforcement learning tasks

Long Context Question Answering via Supervised Contrastive Learning

Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

ST-MoE: Designing Stable and Transferable Sparse Expert Models

An Exploratory Study on Code Attention in BERT

Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling

LinkBERT: Pretraining Language Models with Document Links

ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning

Automatic Detection of Entity-Manipulated Text using Factual Knowledge

On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency

Open Relation Modeling: Learning to Define Relations between Entities

From Unstructured Text to Causal Knowledge Graphs: A Transformer-Based Approach

Synthetic Books

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Robustness of different loss functions and their impact on networks learning capability

On Semantic Cognition, Inductive Generalization, and Language Models

Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails

MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding

Enriching a Model's Notion of Belief using a Persistent Memory

Toward AI Assistants That Let Designers Design