Entity · technique

SHapley Additive exPlanations

techniqueactiveshapley-additive-explanations-a2eb6377·2 events·first seen Jun 10, 2026

Aliases: SHapley Additive exPlanations

Co-occurring entities

NIA PREPARE Llama 3.3 70B Instruct SpeechCARE-Adaptive Gating Network From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection Meta Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions

More like this (12)

Shapley valuation Shapley values Trajectory Shapley Value (TSV)Shannon-Hartley Theorem SHAP Extrapolative Weight Averaging Exact Posterior Score Estimation for Solving Linear Inverse Problems From Plausible to Actionable: A Position on LLM Self-Explanations Narrative Explanations Subspace Projection Toward Calibrated Mixture-of-Experts Under Distribution Shift Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models

Recent events (2)

4arXiv · cs.CL·Jun 29, 2026·source ↗

Multi-stage explainability framework translates transformer speech models into clinical cognitive impairment narratives

A new arXiv preprint proposes a framework for making transformer-based speech cognitive impairment detection clinically interpretable by combining SHAP token attribution, linguistic feature analysis, and a four-stage LLM reasoning pipeline using LLaMA-3.1-70B-Instruct. The system is built on the SpeechCARE-Adaptive Gating Network multimodal model (F1=72.11% on NIA PREPARE) and maps outputs to four cognitive-linguistic dimensions. Physician evaluation on 70 samples showed strong alignment with clinical profiles and a System Usability Scale score of 82/100, suggesting practical clinical workflow integration potential.

Evaluation and Benchmarking AI Safety Research NIA PREPARE Llama 3.3 70B Instruct SpeechCARE-Adaptive Gating Network +3 more

3arXiv · cs.LG·Jun 10, 2026·source ↗

LLM-augmented XAI framework with mutual feature interactions for network operations

A new arXiv paper proposes a framework combining LLMs with SHAP-based explainability, augmented by mutual feature interaction data, to generate natural language explanations for AI/ML models used in network operations. The approach is validated on an optical quality-of-transmission estimation task with human evaluators, showing 12.2% and 6.2% improvements in explanation usefulness and scope over a SHAP-only baseline, with 97.5% correctness. The work targets the gap between technical XAI outputs and actionable insights for non-specialist network operators.

Evaluation and Benchmarking SHapley Additive exPlanations Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions