Related papers: Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions

Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions

URL: http://arxiv.org/abs/2606.10942v1
Date: Tue, 09 Jun 2026 14:48:26 GMT
Title: Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions
Abstract summary: Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists.<n>This paper presents a framework specifically designed to address this shortcoming.<n>It employs a structured prompt enriched with mutual feature interaction data to generate human-understandable natural language explanations.
Score: 1.139115821799478
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing technical outputs that are difficult to translate into actionable insights. This paper presents a framework specifically designed to address this shortcoming. It leverages a moderately sized large language model (LLM) and extends beyond the standard use of SHapley Additive exPlanations (SHAP) feature influence values. The framework employs a structured prompt enriched with mutual feature interaction data to generate human-understandable natural language explanations. To validate our framework, we performed an empirical evaluation on an optical quality of transmission (QoT) estimation use case with human evaluators. We collected independent performance evaluations from specialists, which showed a high inter-evaluator agreement. Compared to a state-of-the-art baseline that uses only SHAP feature influence values in a straightforward prompt, our approach improves the explanation usefulness and scope by 12.2% and 6.2%, while achieving 97.5% correctness.

Related papers

Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models [0.4499833362998488]
Energy consumption forecasting relies on increasingly complex machine learning (ML) models.<n>Traditional Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise.<n>This paper introduces the Explainability Assistant, an open-source conversational XAI system.<n>The system achieves 94% intent-parsing accuracy, supports flexible natural language interaction, and adapts to different ML problem types without task-specific fine-tuning.
arXiv Detail & Related papers (2026-09-10T17:40:11Z)
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning [70.72643569128316]
Imitation learning (IL) training an agent to replicate expert behavior from demonstrations.<n>We introduce OVI, an interactive on-policy IL algorithm that is statistically efficient whenever the learner can represent the expert's value function.<n>OVI outperforms offline policy-based (BC), interactive policy-based (DAgger), and offline value-based IL methods, with the largest gains when the learner network is substantially less expressive than the expert's.
arXiv Detail & Related papers (2026-07-31T16:52:47Z)
Agentic Adversarial QA for Improving Domain-Specific LLMs [53.00642389531106]
Large Language Models (LLMs) often struggle to adapt effectively to specialized domains.<n>We propose an adversarial question-generation framework that produces a compact set of semantically challenging questions.
arXiv Detail & Related papers (2026-02-20T10:53:09Z)
A Multimodal XAI Framework for Trustworthy CNNs and Bias Detection in Deep Representation Learning [0.0]
We propose a novel framework that unifies attention-augmented feature fusion, Grad-CAM++-based local explanations, and a Reveal-to-Revise feedback loop for bias detection and mitigation.<n>Our approach achieves 93.2% classification accuracy, 91.6% F1-score, and 78.1% explanation fidelity (IoU-XAI)<n>Our work bridges the gap between performance, transparency, and fairness, highlighting a practical pathway for trustworthy AI in sensitive domains.
arXiv Detail & Related papers (2025-10-14T20:06:09Z)
Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI [3.301842921686179]
We introduce a framework that ensures transparency and human-centered explanations tailored to the needs of experts and non-experts.<n>Our framework encapsulates in one response explanations understandable by non-experts and technical information to experts.
arXiv Detail & Related papers (2025-06-13T21:41:07Z)
Learning to Generate and Evaluate Fact-checking Explanations with Transformers [10.970249299147866]
Research contributes to the field of Explainable Artificial Antelligence (XAI) We develop transformer-based fact-checking models that contextualise and justify their decisions by generating human-accessible explanations. We emphasise the need for aligning Artificial Intelligence (AI)-generated explanations with human judgements.
arXiv Detail & Related papers (2024-10-21T06:22:51Z)
SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals [0.0]
This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals. SCENE provides valuable insights into the strengths and limitations of various XAI techniques.
arXiv Detail & Related papers (2024-08-08T16:36:24Z)
Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
arXiv Detail & Related papers (2024-04-23T11:45:32Z)
Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
arXiv Detail & Related papers (2023-09-07T01:35:24Z)
Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
arXiv Detail & Related papers (2021-06-14T20:48:48Z)
A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis [73.74885246830611]
We propose a novel dependency syntactic knowledge augmented interactive architecture with multi-task learning for end-to-end ABSA. This model is capable of fully exploiting the syntactic knowledge (dependency relations and types) by leveraging a well-designed Dependency Relation Embedded Graph Convolutional Network (DreGcn) Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2020-04-04T14:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.