Alert button
Picture for Peter Clark

Peter Clark

Alert button

Memory-assisted prompt editing to improve GPT-3 after deployment

Jan 16, 2022
Aman Madaan, Niket Tandon, Peter Clark, Yiming Yang

Figure 1 for Memory-assisted prompt editing to improve GPT-3 after deployment
Figure 2 for Memory-assisted prompt editing to improve GPT-3 after deployment
Figure 3 for Memory-assisted prompt editing to improve GPT-3 after deployment
Figure 4 for Memory-assisted prompt editing to improve GPT-3 after deployment
Viaarxiv icon

Improving scripts with a memory of natural feedback

Dec 16, 2021
Niket Tandon, Aman Madaan, Peter Clark, Yiming Yang

Figure 1 for Improving scripts with a memory of natural feedback
Figure 2 for Improving scripts with a memory of natural feedback
Figure 3 for Improving scripts with a memory of natural feedback
Figure 4 for Improving scripts with a memory of natural feedback
Viaarxiv icon

DREAM: Uncovering Mental Models behind Language Models

Dec 16, 2021
Yuling Gu, Bhavana Dalvi Mishra, Peter Clark

Figure 1 for DREAM: Uncovering Mental Models behind Language Models
Figure 2 for DREAM: Uncovering Mental Models behind Language Models
Figure 3 for DREAM: Uncovering Mental Models behind Language Models
Figure 4 for DREAM: Uncovering Mental Models behind Language Models
Viaarxiv icon

Interscript: A dataset for interactive learning of scripts through error feedback

Dec 16, 2021
Niket Tandon, Aman Madaan, Peter Clark, Keisuke Sakaguchi, Yiming Yang

Figure 1 for Interscript: A dataset for interactive learning of scripts through error feedback
Figure 2 for Interscript: A dataset for interactive learning of scripts through error feedback
Figure 3 for Interscript: A dataset for interactive learning of scripts through error feedback
Figure 4 for Interscript: A dataset for interactive learning of scripts through error feedback
Viaarxiv icon

How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI

Oct 27, 2021
Ashwin Kalyan, Abhinav Kumar, Arjun Chandrasekaran, Ashish Sabharwal, Peter Clark

Figure 1 for How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
Figure 2 for How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
Figure 3 for How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
Figure 4 for How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
Viaarxiv icon

Think about it! Improving defeasible reasoning by first modeling the question scenario

Oct 24, 2021
Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Peter Clark, Yiming Yang, Eduard Hovy

Figure 1 for Think about it! Improving defeasible reasoning by first modeling the question scenario
Figure 2 for Think about it! Improving defeasible reasoning by first modeling the question scenario
Figure 3 for Think about it! Improving defeasible reasoning by first modeling the question scenario
Figure 4 for Think about it! Improving defeasible reasoning by first modeling the question scenario
Viaarxiv icon

BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief

Sep 29, 2021
Nora Kassner, Oyvind Tafjord, Hinrich Schütze, Peter Clark

Figure 1 for BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Figure 2 for BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Figure 3 for BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Figure 4 for BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Viaarxiv icon

General-Purpose Question-Answering with Macaw

Sep 06, 2021
Oyvind Tafjord, Peter Clark

Figure 1 for General-Purpose Question-Answering with Macaw
Figure 2 for General-Purpose Question-Answering with Macaw
Figure 3 for General-Purpose Question-Answering with Macaw
Figure 4 for General-Purpose Question-Answering with Macaw
Viaarxiv icon

Improving Neural Model Performance through Natural Language Feedback on Their Explanations

Apr 18, 2021
Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Yiming Yang, Peter Clark, Keisuke Sakaguchi, Ed Hovy

Figure 1 for Improving Neural Model Performance through Natural Language Feedback on Their Explanations
Figure 2 for Improving Neural Model Performance through Natural Language Feedback on Their Explanations
Figure 3 for Improving Neural Model Performance through Natural Language Feedback on Their Explanations
Figure 4 for Improving Neural Model Performance through Natural Language Feedback on Their Explanations
Viaarxiv icon

Explaining Answers with Entailment Trees

Apr 17, 2021
Bhavana Dalvi, Peter Jansen, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter Clark

Figure 1 for Explaining Answers with Entailment Trees
Figure 2 for Explaining Answers with Entailment Trees
Figure 3 for Explaining Answers with Entailment Trees
Figure 4 for Explaining Answers with Entailment Trees
Viaarxiv icon