ACL Findings2025
Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery
Abstract
Concept-based explainable approaches have emerged as a promising method in explainable AI because they can interpret models in a way that aligns with human reasoning. However, their adaption in the text domain remains limited. Most existing methods rely on predefined concept annotations and cannot discover unseen concepts, while other methods that extract concepts without supervision often produce explanations that are not intuitively comprehensible to humans, potentially diminishing user trust. These methods fall short of discovering comprehensible concepts automatically. To address this issue, we propose ECO-Concept, an intrinsically interpretable framework to discover comprehensible concepts with no concept annotations. ECO-Concept first utilizes an object-centric architecture to extract semantic concepts automatically. Then the comprehensibility of the extracted concepts is evaluated by large language models. Finally, the evaluation result guides the subsequent model fine-tuning to obtain more understandable explanations. Experiments show that our method achieves superior performance across diverse tasks. Further concept evaluations validate that the concepts learned by ECO-Concept surpassed current counterparts in comprehensibility.
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.
Lineage
- Concept Activation Regions: A Generalized Framework For Concept-Based Explanations cites Concept Bottleneck Models
- Concept Activation Regions: A Generalized Framework For Concept-Based Explanations cites On Completeness-aware Concept-Based Explanations in Deep Neural Networks
- On Completeness-aware Concept-Based Explanations in Deep Neural Networks cites Concept Bottleneck Models
Builds on17
- Object-Centric Learning with Slot AttentionFrancesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran et al.NeurIPS 2020 · 1,275 citations
- Concept Bottleneck ModelsPang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann et al.ICML 2020 · 1,233 citations
- On Completeness-aware Concept-Based Explanations in Deep Neural NetworksChih-Kuan Yeh, Been Kim, Sercan Ömer Arik, Chun-Liang Li et al.NeurIPS 2020 · 390 citations
- Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation VectorsRuihan Zhang, Prashan Madumal, Tim Miller, Krista A. Ehinger et al.AAAI 2021 · 140 citations
- Concept Activation Regions: A Generalized Framework For Concept-Based ExplanationsJonathan Crabbé, Mihaela van der SchaarNeurIPS 2022 · 88 citations
Related papers
- Towards Compositionality in Concept LearningAdam Stein, Aaditya Naik, Yinjun Wu, Mayur Naik et al.ICML 2024 · 11 citations
- Explain Any Concept: Segment Anything Meets Concept-Based ExplanationAo Sun, Pingchuan Ma, Yuanyuan Yuan, Shuai WangNeurIPS 2023 · 69 citations
- Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation LearningNavita Goyal, Hal Daumé III, Alexandre Drouin, Dhanya SridharNeurIPS 2025 · 8 citations
- ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language ModelsHaoxuan Li, Zhen Wen, Qiqi Jiang, Chenxiao Li et al.IEEE VIS 2025 · 3 citations
- Understanding Inter-Concept Relationships in Concept-Based ModelsNaveen Raman, Mateo Espinosa Zarlenga, Mateja JamnikICML 2024 · 12 citations
