Lune

ACL Findings2023

A Hierarchical Explanation Generation Method Based on Feature Interaction Detection

Yiming Ju, Yuanzhe Zhang, Kang Liu, Jun Zhao

Abstract

The opaqueness of deep NLP models has motivated efforts to explain how deep models predict. Recently, work has introduced hierarchical attribution explanations, which calculate attribution scores for compositional text hierarchically to capture compositional semantics. Existing work on hierarchical attributions tends to limit the text groups to a continuous text span, which we call the connecting rule. While easy for humans to read, limiting the attribution unit to a continuous span might lose important long-distance feature interactions for reflecting model predictions. In this work, we introduce a novel strategy for capturing feature interactions and employ it to build hierarchical explanations without the connecting rule. The proposed method can convert ubiquitous non-hierarchical explanations (e.g., LIME) into their corresponding hierarchical versions. Experimental results show the effectiveness of our approach in building high-quality hierarchical explanations.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Multi-Level Explanations for Generative Language Models cites Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
  • Multi-Level Explanations for Generative Language Models cites Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
  • Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection cites Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
  • Logic Traps in Evaluating Attribution Scores cites Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Multi-Level Explanations for Generative Language ModelsLucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt et al.ACL 2025 · 16 citations

Builds on3

  1. Generating Hierarchical Explanations on Text Classification via Feature Interaction DetectionHanjie Chen, Guangtao Zheng, Yangfeng JiACL 2020 · 85 citations
  2. Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence ModelsXisen Jin, Zhongyu Wei, Junyi Du, Xiangyang Xue et al.ICLR 2020 · 55 citations
  3. Logic Traps in Evaluating Attribution ScoresYiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang et al.ACL 2022

Related papers

  1. PE: A Poincare Explanation Method for Fast Text Hierarchy GenerationQian Chen, Dongyang Li, Xiaofeng He, Hongzhao Li et al.EMNLP Findings 2024
  2. Asymmetric feature interaction for interpreting model predictionsXiaolei Lu, Jianghong Ma, Haode ZhangACL Findings 2023 · 3 citations
  3. InteDisUX: Intepretation-Guided Discriminative User-Centric Explanation for Time SeriesViet-Hung Tran, Zichi Zhang, Tuan Dung Pham, Ngoc Phu Doan et al.AAAI 2025
  4. Latent Concept-based Explanation of NLP ModelsXuemin Yu, Fahim Dalvi, Nadir Durrani, Marzia Nouri et al.EMNLP 2024 · 3 citations
  5. Self-Attention Attribution: Interpreting Information Interactions Inside TransformerYaru Hao, Li Dong, Furu Wei, Ke XuAAAI 2021 · 282 citations
Dusk over the sea between two cliffs drawn in fine vertical lines