paper-with-me

홈 › Papers

ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation

2025-12-08 · Latifa Dwiyanti, Sergio Ryan Wibisono, Hidetaka Nambo arxiv

Explainable Artificial Intelligence (XAI) has become an increasingly important area of research, particularly as machine learning models are deployed in high-stakes domains. Among various XAI approaches, SHAP (SHapley Additive exPlanations) has gained prominence due to its ability to provide both global and local explanations across different machine learning models. While SHAP effectively visualizes feature importance, it often lacks contextual explanations that are meaningful for end-users, especially those without technical backgrounds. To address this gap, we propose a Python package that extends SHAP by integrating it with a large language model (LLM), specifically OpenAI's GPT, to generate contextualized textual explanations. This integration is guided by user-defined parameters (such as feature aliases, descriptions, and additional background) to tailor the explanation to both the model context and the user perspective. We hypothesize that this enhancement can improve the perceived understandability of SHAP explanations. To evaluate the effectiveness of the proposed package, we applied it in a healthcare-related case study and conducted user evaluations involving real end-users. The results, based on Likert-scale surveys and follow-up interviews, indicate that the generated explanations were perceived as more understandable and contextually appropriate compared to visual-only outputs. While the findings are preliminary, they suggest that combining visualization with contextualized text may support more user-friendly and trustworthy model explanations.

📄 PDF Abstract BibTeX arXiv:2512.07178

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

Counterfactual Explanations for Deep Learning-Based Traffic Forecasting

2024-05-01 · Rushan Wang, Yanan Xin, Yatao Zhang, Fernando Perez-Cruz 외

Deep learning models are widely used in traffic forecasting and have achieved state-of-the-art prediction accuracy. However, the black-box nature of those models makes the results difficult to interpret by users. This st…

counterfactualDeep Learning

The Effect of Enforcing Fairness on Reshaping Explanations in Machine Learning Models

2025-12-01 · Joshua Wolff Anderson, Shyam Visweswaran arxiv

Trustworthy machine learning in healthcare requires strong predictive performance, fairness, and explanations. While it is known that improving fairness can affect predictive performance, little is known about how fairne…

Feature Importance

TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents

2023-12-03 · James Enouen, Hootan Nakhost, Sayna Ebrahimi, Sercan O Arik 외

Large language models (LLMs) have attracted huge interest in practical applications given their increasingly accurate responses and coherent reasoning abilities. Given their nature as black-boxes using complex reasoning …

Question AnsweringText Generation

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection

2023-12-19 · Gwladys Kelodjou, Laurence Rozé, Véronique Masson, Luis Galárraga 외

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple con…

Decision MakingFairness

Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI

2026-05-29 · Mert Yazan, Suzan Verberne, Frederik Bungaran Ishak Situmeang arxiv

Artificial Intelligence (AI) agents personalize their responses by tailoring explanations to users' backgrounds, interests, and prior interactions, referred to as contextualization. Personalization has been identified as…