SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.01378 · EMNLP · 2021

Contrastive Explanations for Model Interpretability

Swabha Swayamdipta, Yejin Choi, Yoav Goldberg, Shauli Ravfogel, Yanai Elazar, Alon Jacovi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Contrastive explanations clarify why an event occurred in contrast to another. They are inherently intuitive to humans to both produce and comprehend. We propose a method to produce contrastive explanations in the latent space, via a projection of the input representation, such that only the features that differentiate two potential decisions are captured. Our modification allows model behavior to consider only contrastive reasoning, and uncover which aspects of the input are useful for and against particular decisions. Additionally, for a given input feature, our contrastive explanations can answer for which label, and against which alternative label, is the feature useful. We produce contrastive explanations via both highlevel abstract concept attribution and low-level input token/span attribution for two NLP classification benchmarks. Our findings demonstrate the ability of label-contrastive explanations to provide fine-grained interpretability of model decisions. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.01378")
get_code_for_paper("2103.01378")
have("2103.01378")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.01378.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.01378.svg)](https://syntology.ai/paper/2103.01378)

Connect an agent — have() is free.