paper-with-me

홈 › Papers

Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

2020-04-07 · ACL 2020 6 · Alon Jacovi, Yoav Goldberg

With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. But what is interpretability, and what constitutes a high-quality interpretation? In this opinion piece we reflect on the current state of interpretability evaluation research. We call for more clearly differentiating between different desired criteria an interpretation should satisfy, and focus on the faithfulness criteria. We survey the literature with respect to faithfulness evaluation, and arrange the current approaches around three assumptions, providing an explicit form to how faithfulness is "defined" by the community. We provide concrete guidelines on how evaluation of interpretation methods should and should not be conducted. Finally, we claim that the current binary definition for faithfulness sets a potentially unrealistic bar for being considered faithful. We call for discarding the binary notion of faithfulness in favor of a more graded one, which we believe will be of greater practical utility.

📄 PDF Abstract BibTeX arXiv:2004.03685

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems

2018-06-20 · Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece 외

Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretab…

BIG-bench Machine LearningInterpretable Machine LearningRelation

HumanScore: Benchmarking Human Motions in Generated Videos

2026-04-22 · Yusu Fang, Tiange Xiang, Tian Tan, Narayan Schuetz 외 arxiv

Recent advances in model architectures, compute, and data scale have driven rapid progress in video generation, producing increasingly realistic content. Yet, no prior method systematically measures how faithfully these …

Video Generation

Residualized Similarity for Faithfully Explainable Authorship Verification

2025-10-06 · Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey 외 arxiv

Responsible use of Authorship Verification (AV) systems not only requires high accuracy but also interpretable solutions. More importantly, for systems to be used to make decisions with real-world consequences requires t…

Towards A Rigorous Science of Interpretable Machine Learning

2017-02-28 · Finale Doshi-Velez, Been Kim

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively …

BIG-bench Machine LearningInterpretable Machine LearningPosition

Faithfully Explainable Recommendation via Neural Logic Reasoning

2021-04-16 · NAACL 2021 4 · Yaxin Zhu, Yikun Xian, Zuohui Fu, Gerard de Melo 외

Knowledge graphs (KG) have become increasingly important to endow modern recommender systems with the ability to generate traceable reasoning paths to explain the recommendation process. However, prior research rarely co…

Decision MakingExplainable RecommendationExplanation GenerationKnowledge Graphs+1