TIGTEC : Token Importance Guided TExt Counterfactuals
Counterfactual examples explain a prediction by highlighting changes of instance that flip the outcome of a classifier. This paper proposes TIGTEC, an efficient and modular method for generating sparse, plausible and diverse counterfactual explanations for textual data. TIGTEC is a text editing heuristic that targets and modifies words with high contribution using local feature importance. A new attention-based local feature importance is proposed. Counterfactual candidates are generated and assessed with a cost function integrating semantic distance, while the solution space is efficiently explored in a beam search fashion. The conducted experiments show the relevance of TIGTEC in terms of success rate, sparsity, diversity and plausibility. This method can be used in both model-specific or model-agnostic way, which makes it very convenient for generating counterfactual explanations.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualDiversityFeature ImportanceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
A principle behind dozens of attribution methods is to take the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. A popular Input Marginalization (IM) method (…
Causal InferenceFitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of …
counterfactualExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature ImportanceCounterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models
Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation …
counterfactualDecision MakingFeature ImportanceLanguage ModellingVFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information, but this token redundancy results in significant computational costs. Previous resea…
Counterfactual Multi-Token Fairness in Text Classification
The counterfactual token generation has been limited to perturbing only a single token in texts that are generally short and single sentences. These tokens are often associated with one of many sensitive attributes. With…
AttributeClassificationcounterfactualFairness+3