Timezone: »
To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control.
Recently, it has been shown that Transformer-based models succeed in consistent reasoning over explicit symbolic facts, under a "closed-world" assumption.
However, in an open-domain setup, it is desirable to tap into the vast reservoir of implicit knowledge already encoded in the parameters of pre-trained LMs.
In this work, we provide a first demonstration that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements.
To do this, we describe a procedure for automatically generating datasets that teach a model new reasoning skills, and demonstrate that models learn to effectively perform inference which involves implicit taxonomic and world knowledge, chaining and counting.
Finally, we show that "teaching" models to reason generalizes beyond the training distribution: they successfully compose the usage of multiple reasoning skills in single examples.
Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
Author Information
Alon Talmor (Allen Institute for AI, Tel Aviv University)
Oyvind Tafjord (Allen Institute for AI)
Peter Clark (Allen Institute for AI)
Yoav Goldberg (Allen Institute for AI, Bar Ilan University)
Jonathan Berant (Tel Aviv University)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Spotlight: Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge »
Wed. Dec 9th 04:10 -- 04:20 PM Room Orals & Spotlights: Continual/Meta/Misc Learning
More from the Same Authors
-
2021 : CommonsenseQA 2.0: Exposing the Limits of AI through Gamification »
Alon Talmor · Ori Yoran · Ronan Le Bras · Chandra Bhagavatula · Yoav Goldberg · Yejin Choi · Jonathan Berant -
2022 : Learn to Select Good Examples with Reinforcement Learning for Semi-structured Mathematical Reasoning »
Pan Lu · Liang Qiu · Kai-Wei Chang · Ying Nian Wu · Song-Chun Zhu · Tanmay Rajpurohit · Peter Clark · Ashwin Kalyan -
2022 : LILA: A Unified Benchmark for Mathematical Reasoning »
Swaroop Mishra · Matthew Finlayson · Pan Lu · Leonard Tang · Sean Welleck · Chitta Baral · Tanmay Rajpurohit · Oyvind Tafjord · Ashish Sabharwal · Peter Clark · Ashwin Kalyan -
2023 Poster: Self-Refine: Iterative Refinement with Self-Feedback »
Aman Madaan · Niket Tandon · Prakhar Gupta · Skyler Hallinan · Luyu Gao · Sarah Wiegreffe · Uri Alon · Nouha Dziri · Shrimai Prabhumoye · Yiming Yang · Shashank Gupta · Bodhisattwa Prasad Majumder · Katherine Hermann · Sean Welleck · Amir Yazdanbakhsh · Peter Clark -
2023 Poster: From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces »
Peter Shaw · Mandar Joshi · James Cohan · Jonathan Berant · Panupong Pasupat · Hexiang Hu · Urvashi Khandelwal · Kenton Lee · Kristina N Toutanova -
2022 Spotlight: Lightning Talks 2A-4 »
Sarthak Mittal · Richard Grumitt · Zuoyu Yan · Lihao Wang · Dongsheng Wang · Alexander Korotin · Jiangxin Sun · Ankit Gupta · Vage Egiazarian · Tengfei Ma · Yi Zhou · Yishi Xu · Albert Gu · Biwei Dai · Chunyu Wang · Yoshua Bengio · Uros Seljak · Miaoge Li · Guillaume Lajoie · Yiqun Wang · Liangcai Gao · Lingxiao Li · Jonathan Berant · Huang Hu · Xiaoqing Zheng · Zhibin Duan · Hanjiang Lai · Evgeny Burnaev · Zhi Tang · Zhi Jin · Xuanjing Huang · Chaojie Wang · Yusu Wang · Jian-Fang Hu · Bo Chen · Chao Chen · Hao Zhou · Mingyuan Zhou -
2022 Spotlight: Diagonal State Spaces are as Effective as Structured State Spaces »
Ankit Gupta · Albert Gu · Jonathan Berant -
2022 : Towards Systematic Reasoning with Language Models »
Peter Clark -
2022 Poster: Diagonal State Spaces are as Effective as Structured State Spaces »
Ankit Gupta · Albert Gu · Jonathan Berant -
2022 Poster: Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering »
Pan Lu · Swaroop Mishra · Tanglin Xia · Liang Qiu · Kai-Wei Chang · Song-Chun Zhu · Oyvind Tafjord · Peter Clark · Ashwin Kalyan -
2021 : CommonsenseQA 2.0: Exposing the Limits of AI through Gamification »
Alon Talmor · Ori Yoran · Ronan Le Bras · Chandra Bhagavatula · Yoav Goldberg · Yejin Choi · Jonathan Berant -
2018 Poster: Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction »
Roei Herzig · Moshiko Raboh · Gal Chechik · Jonathan Berant · Amir Globerson -
2018 Poster: Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing »
Chen Liang · Mohammad Norouzi · Jonathan Berant · Quoc V Le · Ni Lao -
2018 Spotlight: Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing »
Chen Liang · Mohammad Norouzi · Jonathan Berant · Quoc V Le · Ni Lao -
2014 Workshop: 4th Workshop on Automated Knowledge Base Construction (AKBC) »
Sameer Singh · Fabian M Suchanek · Sebastian Riedel · Partha Pratim Talukdar · Kevin Murphy · Christopher RĂ© · William Cohen · Tom Mitchell · Andrew McCallum · Jason E Weston · Ramanathan Guha · Boyan Onyshkevych · Hoifung Poon · Oren Etzioni · Ari Kobren · Arvind Neelakantan · Peter Clark