Evaluating Readability and Faithfulness of Concept-based Explanations

• URL: http://arxiv.org/abs/2404.18533v3
• Date: Fri, 04 Oct 2024 01:21:28 GMT
• Title: Evaluating Readability and Faithfulness of Concept-based Explanations
• Authors: Meng Li, Haoran Jin, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, Xiting Wang,
• Abstract summary: Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by Large Language Models. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging.
• Score: 35.48852504832633
• License:
• Abstract: With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by LLMs. Yet their evaluation poses unique challenges, especially due to their non-local nature and high dimensional representation in a model's hidden space. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging. To bridge the gap, we introduce a formal definition of concepts generalizing to diverse concept-based explanations' settings. Based on this, we quantify the faithfulness of a concept explanation via perturbation. We ensure adequate perturbation in the high-dimensional space for different concepts via an optimization problem. Readability is approximated via an automatic and deterministic measure, quantifying the coherence of patterns that maximally activate a concept while aligning with human understanding. Finally, based on measurement theory, we apply a meta-evaluation method for evaluating these measures, generalizable to other types of explanations or tasks as well. Extensive experimental analysis has been conducted to inform the selection of explanation evaluation measures.

Related papers

• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• A survey on Concept-based Approaches For Model Improvement [2.1516043775965565]
  Concepts are known to be the thinking ground of humans. We provide a systematic review and taxonomy of various concept representations and their discovery algorithms in Deep Neural Networks (DNNs) We also provide details on concept-based model improvement literature marking the first comprehensive survey of these methods.
  arXiv  Detail & Related papers  (2024-03-21T17:09:20Z)
• An Axiomatic Approach to Model-Agnostic Concept Explanations [67.84000759813435]
  We propose an approach to concept explanations that satisfy three natural axioms: linearity, recursivity, and similarity. We then establish connections with previous concept explanation methods, offering insight into their varying semantic meanings.
  arXiv  Detail & Related papers  (2024-01-12T20:53:35Z)
• ConcEPT: Concept-Enhanced Pre-Training for Language Models [57.778895980999124]
  ConcEPT aims to infuse conceptual knowledge into pre-trained language models. It exploits external entity concept prediction to predict the concepts of entities mentioned in the pre-training contexts. Results of experiments show that ConcEPT gains improved conceptual knowledge with concept-enhanced pre-training.
  arXiv  Detail & Related papers  (2024-01-11T05:05:01Z)
• Estimation of Concept Explanations Should be Uncertainty Aware [39.598213804572396]
  We study a specific kind called Concept Explanations, where the goal is to interpret a model using human-understandable concepts. Although popular for their easy interpretation, concept explanations are known to be noisy. We propose an uncertainty-aware Bayesian estimation method to address these issues, which readily improved the quality of explanations.
  arXiv  Detail & Related papers  (2023-12-13T11:17:27Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• A Unified Concept-Based System for Local, Global, and Misclassification Explanations [13.321794212377949]
  We present a unified concept-based system for unsupervised learning of both local and global concepts. Our primary objective is to uncover the intrinsic concepts underlying each data category by training surrogate explainer networks. Our approach facilitates the explanation of both accurate and erroneous predictions.
  arXiv  Detail & Related papers  (2023-06-06T09:28:37Z)
• Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees [1.9465727478912072]
  We propose Multi-dimensional Concept Discovery (MCD) as an extension of previous approaches that fulfills a completeness relation on the level of concepts. We empirically demonstrate the superiority of MCD against more constrained concept definitions.
  arXiv  Detail & Related papers  (2023-01-27T18:53:19Z)
• Towards Robust Metrics for Concept Representation Evaluation [25.549961337814523]
  Concept learning models have been shown to be prone to encoding impurities in their representations. We propose novel metrics for evaluating the purity of concept representations in both approaches.
  arXiv  Detail & Related papers  (2023-01-25T00:40:19Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• Translational Concept Embedding for Generalized Compositional Zero-shot Learning [73.60639796305415]
  Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework.
  arXiv  Detail & Related papers  (2021-12-20T21:27:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.