XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.
Llms for explainable ai: A comprehensive survey
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
background 2polarities
background 2representative citing papers
COMPASS formalizes prompt engineering as a POMDP-based cognitive decision process for self-adaptive generation of task plan explanations via LLMs.
M2-PALE extracts process models from multi-agent MCTS-Minimax execution traces using Alpha Miner, iDHM and Inductive Miner, then uses LLMs to generate causal explanations, shown in a small checkers setting.
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
Adversarial explanation attacks preserve nearly all human trust in wrong AI outputs by using persuasive framing, shown in a study varying reasoning, evidence, style, and format with over 200 participants.
AnTenA uses task-agnostic and task-specific LLM prompts to explain co-clustered patterns from tensor decomposition and evaluates them on forward and backward inference tasks.
A survey formalizing responsibility-oriented goals for wireless XAI, developing a taxonomy of explainability approaches, reviewing PHY layer applications, and discussing open challenges including performance tradeoffs and LLM integration.
ExAI5G combines Transformer-based intrusion detection with surrogate decision trees and LLM-evaluated explanations to deliver 99.9% accuracy and 16 high-fidelity logical rules on 5G IoT traffic while preserving performance.
Encoder-based LLMs detect SDN intrusions with decisions driven by meaningful traffic behaviors, as validated by attribution analysis aligning with established intrusion principles.
The study applies Bayesian uncertainty propagation to agentic RAG pipelines on StrategyQA and HotpotQA, reporting better discrimination on HotpotQA than on StrategyQA using standard calibration and selective-prediction metrics.
citing papers explorer
-
XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.
-
Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs
COMPASS formalizes prompt engineering as a POMDP-based cognitive decision process for self-adaptive generation of task plan explanations via LLMs.
-
M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs
M2-PALE extracts process models from multi-agent MCTS-Minimax execution traces using Alpha Miner, iDHM and Inductive Miner, then uses LLMs to generate causal explanations, shown in a small checkers setting.
-
Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
-
When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
Adversarial explanation attacks preserve nearly all human trust in wrong AI outputs by using persuasive framing, shown in a study varying reasoning, evidence, style, and format with over 200 participants.
-
AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models
AnTenA uses task-agnostic and task-specific LLM prompts to explain co-clustered patterns from tensor decomposition and evaluates them on forward and backward inference tasks.
-
Explainable AI for Next-Generation Wireless Physical Layer: Basics, State-of-the-Art, and Open Challenges
A survey formalizing responsibility-oriented goals for wireless XAI, developing a taxonomy of explainability approaches, reviewing PHY layer applications, and discussing open challenges including performance tradeoffs and LLM integration.
-
ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks
ExAI5G combines Transformer-based intrusion detection with surrogate decision trees and LLM-evaluated explanations to deliver 99.9% accuracy and 16 high-fidelity logical rules on 5G IoT traffic while preserving performance.
-
Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models
Encoder-based LLMs detect SDN intrusions with decisions driven by meaningful traffic behaviors, as validated by attribution analysis aligning with established intrusion principles.
-
Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering
The study applies Bayesian uncertainty propagation to agentic RAG pipelines on StrategyQA and HotpotQA, reporting better discrimination on HotpotQA than on StrategyQA using standard calibration and selective-prediction metrics.