# Weakly- and Semi-supervised Evidence Extraction

arXiv: https://arxiv.org/abs/2011.01459 · HTML: https://mlsanity.com/paper/2011.01459/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 16 of 16)

- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU](https://mlsanity.com/paper/2109.08259/) (2021)
- [Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction](https://mlsanity.com/paper/2112.10424/) (2021)
- [Human-Centric Research for NLP: Towards a Definition and Guiding Questions](https://mlsanity.com/paper/2207.04447/) (2022)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [Diagnostics-Guided Explanation Generation](https://mlsanity.com/paper/2109.03756/) (2021)
- [Are Training Resources Insufficient? Predict First Then Explain!](https://mlsanity.com/paper/2110.02056/) (2021)
- [Practical Benefits of Feature Feedback Under Distribution Shift](https://mlsanity.com/paper/2110.07566/) (2021)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [Making Document-Level Information Extraction Right for the Right Reasons](https://mlsanity.com/paper/2110.07686/) (2021)
- [To Aggregate or Not to Aggregate. That is the Question: A Case Study on Annotation Subjectivity in Span Prediction](https://mlsanity.com/paper/2408.02257/) (2024)
- [Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers](https://mlsanity.com/paper/2303.07991/) (2023)
- [U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension](https://mlsanity.com/paper/2210.02621/) (2022)
- [Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals](https://mlsanity.com/paper/2210.11805/) (2022)
- [Slogans or Stance? A Label-Light Diagnostic for Entrepreneurial-Discourse Measurement on Chinese SOE Speeches](https://mlsanity.com/paper/2605.29188/) (2026)

## Abstract (arXiv)

For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, additional annotations marking supporting evidence may only be available for a minority of training examples (if available at all). In this paper, we propose new methods to combine few evidence annotations (strong semi-supervision) with abundant document-level labels (weak supervision) for the task of evidence extraction. Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task. Our approach yields substantial gains with as few as hundred evidence annotations. Code and datasets to reproduce our work are available at https://github.com/danishpruthi/evidence-extraction.