Peter Hase | DeepAI

DeepAI AI Chat

Featured Co-authors

Caiming Xiong
192 publications
Mohit Bansal
164 publications
Cynthia Rudin
85 publications
Mona Diab
52 publications
Asli Celikyilmaz
49 publications
Xian Li
46 publications
Xiang Zhou
46 publications
Been Kim
39 publications
Shiyue Zhang
19 publications
Veselin Stoyanov
18 publications
Nazneen Fatema Rajani
18 publications

∙ 01/10/2023

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

Language models are known to learn a great quantity of factual informati...

2 Peter Hase, et al. ∙

∙ 11/14/2022

Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations

Recent work on explainable NLP has shown that few-shot prompting can ena...

5 Swarnadeep Saha, et al. ∙

∙ 09/21/2022

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

Current abstractive summarization models either suffer from a lack of cl...

10 Swarnadeep Saha, et al. ∙

∙ 06/22/2022

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

Many past works aim to improve visual reasoning in models by supervising...

8 Zhuofan Ying, et al. ∙

∙ 03/14/2022

GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models

Providing natural language instructions in prompts is a useful new parad...

1 Archiki Prasad, et al. ∙

∙ 11/26/2021

Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs

Do language models have beliefs about the world? Dennett (1995) famously...

5 Peter Hase, et al. ∙

∙ 11/01/2021

Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

The problem of identifying algorithmic recourse for people affected by m...

4 Prateek Yadav, et al. ∙

∙ 06/01/2021

Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals

Feature importance (FI) estimates are a popular form of explanation, and...

7 Peter Hase, et al. ∙

∙ 02/03/2021

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data

Many methods now exist for conditioning model outputs on task instructio...

9 Peter Hase, et al. ∙

∙ 12/31/2020

FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Influence functions approximate the 'influences' of training data-points...

9 Han Guo, et al. ∙

∙ 10/08/2020

Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?

Data collection for natural language (NL) understanding tasks has increa...

7 Peter Hase, et al. ∙

∙ 05/04/2020

Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?

Algorithmic approaches to interpreting machine learning models have prol...

98 Peter Hase, et al. ∙

∙ 06/25/2019

Interpretable Image Recognition with Hierarchical Prototypes

Vision models are interpretable when they classify objects on the basis ...

2 Peter Hase, et al. ∙

∙ 11/13/2018

Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation

We provide code that produces beautiful poetry. Our sonnet-generation al...

0 John Benhart, et al. ∙