# A Framework for Rationale Extraction for Deep QA models

Source: [A Framework for Rationale Extraction for Deep QA models](<https://www.sota2.com/research/paper/68fa6afe1e209131cea2b957>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:50.176Z

Authors: Sahana Ramnath, Preksha Nema, Deep Sahni, Mitesh M. Khapra

Published: 2021-10-09T18:02:55.000Z

## Abstract

As neural-network-based QA models become deeper and more complex, there is a demand for robust frameworks which can access a model's rationale for its prediction. Current techniques that provide insights on a model's working are either dependent on adversarial datasets or are proposing models with explicit explanation generation components. These techniques are time-consuming and challenging to extend to existing models and new datasets. In this work, we use \`Integrated Gradients' to extract rationale for existing state-of-the-art models in the task of Reading Comprehension based Question Answering (RCQA). On detailed analysis and comparison with collected human rationales, we find that though ~40-80% words of extracted rationale coincide with the human rationale (precision), only 6-19% of human rationale is present in the extracted rationale (recall).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.04620>)

[PDF](<https://arxiv.org/pdf/2110.04620.pdf>)
