Search Results for author: Sarah Wiegreffe

Found 13 papers, 8 papers with code

Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals

no code implementations16 Nov 2023 Yanai Elazar, Bhargavi Paranjape, Hao Peng, Sarah Wiegreffe, Khyathi Raghavi, Vivek Srikumar, Sameer Singh, Noah A. Smith

Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e. g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance.

counterfactual Natural Language Inference +1

Editing Common Sense in Transformers

no code implementations24 May 2023 Anshita Gupta, Debanjan Mondal, Akshay Krishna Sheshadri, Wenlong Zhao, Xiang Lorraine Li, Sarah Wiegreffe, Niket Tandon

However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer.

Common Sense Reasoning Model Editing +1

Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy

1 code implementation24 May 2023 Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord, Peter Clark, Ashish Sabharwal

For example, both normalization and prompting methods for reducing SFC can be ineffective or even detrimental to task performance for some LMs.

Multiple-choice valid

Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes

no code implementations16 Apr 2022 Kaige Xie, Sarah Wiegreffe, Mark Riedl

We show that decomposition is an effective form of probing QA systems as well as a promising approach to explanation generation.

Explanation Generation Multi-hop Question Answering +1

Reframing Human-AI Collaboration for Generating Free-Text Explanations

1 code implementation NAACL 2022 Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, Yejin Choi

We create a pipeline that combines GPT-3 with a supervised filter that incorporates binary acceptability judgments from humans in the loop.

Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning

1 code implementation4 May 2021 Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark Riedl

Transformer-based language model approaches to automated story generation currently provide state-of-the-art results.

Language Modelling Story Generation

Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing

no code implementations24 Feb 2021 Sarah Wiegreffe, Ana Marasović

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual explanations.

Data Augmentation

Measuring Association Between Labels and Free-Text Rationales

1 code implementation EMNLP 2021 Sarah Wiegreffe, Ana Marasović, Noah A. Smith

In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance.

Decision Making Feature Importance +2

Learning to Faithfully Rationalize by Construction

2 code implementations ACL 2020 Sarthak Jain, Sarah Wiegreffe, Yuval Pinter, Byron C. Wallace

In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet comprises tokens that indeed informed the model's prediction, it is a faithful explanation.

Feature Importance text-classification +1

Attention is not not Explanation

2 code implementations IJCNLP 2019 Sarah Wiegreffe, Yuval Pinter

We show that even when reliable adversarial distributions can be found, they don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.

Decision Making Experimental Design

Explainable Prediction of Medical Codes from Clinical Text

3 code implementations NAACL 2018 James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, Jacob Eisenstein

Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes.

Medical Code Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.