paper-with-me

홈 › Papers

SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals

2024-08-08 · Haoran Zheng, Utku Pamuksuz

Explainable Artificial Intelligence (XAI) plays a crucial role in enhancing the transparency and accountability of AI models, particularly in natural language processing (NLP) tasks. However, popular XAI methods such as LIME and SHAP have been found to be unstable and potentially misleading, underscoring the need for a standardized evaluation approach. This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method that leverages large language models (LLMs) to generate Soft Counterfactual explanations in a zero-shot manner. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals without extensive fine-tuning. SCENE adopts Validitysoft and Csoft metrics to assess the effectiveness of model-agnostic XAI methods in text classification tasks. Applied to CNN, RNN, and Transformer architectures, SCENE provides valuable insights into the strengths and limitations of various XAI techniques.

📄 PDF Abstract BibTeX arXiv:2408.04575

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)text-classificationText Classification

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
SHAP 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)

2020-05-26 · Mark T. Keane, Barry Smyth

Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual…

counterfactualExplainable Artificial Intelligence (XAI)

From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI

2025-05-19 · Galit Shmueli, David Martens, Jaewon Yoo, Travis Greene

Counterfactuals play a pivotal role in the two distinct data science fields of causal inference (CI) and explainable artificial intelligence (XAI). While the core idea behind counterfactuals remains the same in both fiel…

Causal InferencecounterfactualExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

2019-05-19 · Ramaravind Kommiya Mothilal, Amit Sharma, Chenhao Tan

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show pe…

BIG-bench Machine LearningcounterfactualDiversityPoint Processes

What-If Explanations Over Time: Counterfactuals for Time Series Classification

2026-03-29 · Udo Schlegel, Thomas Seidl arxiv

Counterfactual explanations emerge as a powerful approach in explainable AI, providing what-if scenarios that reveal how minimal changes to an input time series can alter the model's prediction. This work presents a surv…

Time Series ClassificationTime Series Forecasting

Explainable AI for Software Engineering

2020-12-03 · Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, John Grundy

Artificial Intelligence/Machine Learning techniques have been widely used in software engineering to improve developer productivity, the quality of software systems, and decision-making. However, such AI/ML models for so…

BIG-bench Machine LearningDecision Making