Imagen de Portada

llmSHAP: A Principled Approach to LLM Explainability

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Naudot, Filip, Sundqvist, Tobias, Kampik, Timotheus
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Set Contribution Functions for Quantitative Bipolar Argumentation and their Principles
por: Naudot, Filip, et al.
Publicado: (2025)

xSemAD: Explainable Semantic Anomaly Detection in Event Logs Using Sequence-to-Sequence Models
por: Busch, Kiran, et al.
Publicado: (2024)

Specification, Application, and Operationalization of a Metamodel of Fairness
por: Mendez, Julian Alfredo, et al.
Publicado: (2025)

Contribution Functions for Quantitative Bipolar Argumentation Graphs: A Principle-based Analysis
por: Kampik, Timotheus, et al.
Publicado: (2024)

Disagree and Commit: Degrees of Argumentation-based Agreements
por: Kampik, Timotheus, et al.
Publicado: (2024)

Can Proof Assistants Verify Multi-Agent Systems?
por: Mendez, Julian Alfredo, et al.
Publicado: (2025)

Conversational Process Model Redesign
por: Klievtsova, Nataliia, et al.
Publicado: (2025)

Change in Quantitative Bipolar Argumentation: Sufficient, Necessary, and Counterfactual Explanations
por: Kampik, Timotheus, et al.
Publicado: (2025)

Contestability in Quantitative Argumentation
por: Yin, Xiang, et al.
Publicado: (2025)

AgentSimulator: An Agent-based Approach for Data-driven Business Process Simulation
por: Kirchdorfer, Lukas, et al.
Publicado: (2024)

Strength Change Explanations in Quantitative Argumentation
por: Kampik, Timotheus, et al.
Publicado: (2026)

Formal Foundations of Agentic Business Process Management
por: De Giacomo, Giuseppe, et al.
Publicado: (2026)

Implementing Agents in JavaScript
por: Kampik, Timotheus
Publicado: (2025)

Conversational Process Modeling: Can Generative AI Empower Domain Experts in Creating and Redesigning Process Models?
por: Klievtsova, Nataliia, et al.
Publicado: (2023)

An approach for systematic decomposition of complex llm tasks
por: Zhou, Tianle, et al.
Publicado: (2025)

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
por: Salih, Ahmed, et al.
Publicado: (2023)

dots.llm1 Technical Report
por: Huo, Bi, et al.
Publicado: (2025)

Expressive Power and Complexity Results for SIGNAL, an Industry-scale Process Query Language
por: Kampik, Timotheus, et al.
Publicado: (2023)

CQD-SHAP: Explainable Complex Query Answering via Shapley Values
por: Abbasi, Parsa, et al.
Publicado: (2025)

Enhancing SHAP Explainability for Diagnostic and Prognostic ML Models in Alzheimer Disease
por: Guillén, Pablo, et al.
Publicado: (2026)

Configurable multi-agent framework for scalable and realistic testing of llm-based agents
por: Wang, Sai, et al.
Publicado: (2025)

Eliminating stability hallucinations in llm-based tts models via attention guidance
por: Wang, ShiMing, et al.
Publicado: (2025)

Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption
por: Wong, Kester, et al.
Publicado: (2025)

The Distributional Uncertainty of the SHAP score in Explainable Machine Learning
por: Cifuentes, Santiago, et al.
Publicado: (2024)

JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles
por: Nasrabadi, Dom
Publicado: (2024)

PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
por: Fumagalli, Fabian, et al.
Publicado: (2026)

SHAP Distance: An Explainability-Aware Metric for Evaluating the Semantic Fidelity of Synthetic Tabular Data
por: Yu, Ke, et al.
Publicado: (2025)

Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling
por: Srisumrith, Norrakith, et al.
Publicado: (2026)

Interaction Tensor SHAP
por: Hasegawa, Hiroki, et al.
Publicado: (2025)

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning
por: Cao, Zhuo, et al.
Publicado: (2025)

Towards trustable SHAP scores
por: Letoffe, Olivier, et al.
Publicado: (2024)

CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis
por: Chen, Qian, et al.
Publicado: (2025)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
por: Trivedi, Prashant, et al.
Publicado: (2025)

Privacy-Preserving Inconsistency Measurement
por: Corea, Carl, et al.
Publicado: (2025)

Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
por: Boetius, David, et al.
Publicado: (2026)

AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation
por: Horovicz, Miriam
Publicado: (2025)

Explainable Fall Detection for Elderly Monitoring via Temporally Stable SHAP in Skeleton-Based Human Activity Recognition
por: Saleh, Mohammad, et al.
Publicado: (2026)

ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation
por: Dwiyanti, Latifa, et al.
Publicado: (2025)

Explanation Multiplicity in SHAP: Characterization and Assessment
por: Hwang, Hyunseung, et al.
Publicado: (2026)

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding
por: Li, Huayu, et al.
Publicado: (2026)