paper-with-me

Papers

Active Learning++: Incorporating Annotator's Rationale using Local Model Explanation

2020-09-06 · Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang, Klaus Mueller

We propose a new active learning (AL) framework, Active Learning++, which can utilize an annotator's labels as well as its rationale. Annotators can provide their rationale for choosing a label by ranking input features based on their importance for a given query. To incorporate this additional input, we modified the disagreement measure for a bagging-based Query by Committee (QBC) sampling strategy. Instead of weighing all committee models equally to select the next instance, we assign higher weight to the committee model with higher agreement with the annotator's ranking. Specifically, we generated a feature importance-based local explanation for each committee model. The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model. This approach is applicable to any kind of ML model using model-agnostic techniques to generate local explanation such as LIME. With a simulation study, we show that our framework significantly outperforms a QBC based vanilla AL framework.

📄 PDF Abstract BibTeX arXiv:2009.04568

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningFeature Importance

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales

2026-04-23 · Olufunke O. Sarumi, Charles Welch, Daniel Braun arxiv

Beyond exploring disaggregated labels for modeling perspectives, annotator rationales provide fine-grained signals of individual perspectives. In this work, we propose a framework for jointly modeling annotator-specific …

Natural Language InferenceExplanation Generation

Free-text Rationale Generation under Readability Level Control

2024-07-01 · Yi-Sheng Hsu, Nils Feldhus, Sherzod Hakimov

Free-text rationales justify model decisions in natural language and thus become likable and accessible among approaches to explanation across many tasks. However, their effectiveness can be hindered by misinterpretation…

HallucinationText Generation

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

2021-06-25 · Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz, Julian McAuley

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view o…

Decision Making

Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture

2023-05-22 · Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis 외

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), t…

Active LearningDecision MakingDiversityExplanation Generation+1

Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers

2025-06-12 · Xanh Ho, Sunisth Kumar, Yun-Ang Wu, Florian Boudin 외

Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little…

Claim Verification