paper-with-me

Papers

When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation

2026-01-14 · Jing Ren, Bowen Li, Ziqi Xu, Xikun Zhang, Haytham Fayek, Xiaodong Li arxiv

Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While KG-RAG improves factual accuracy in complex tasks, existing KG-RAG models are often severely overconfident, producing high-confidence predictions even when retrieved sub-graphs are incomplete or unreliable, which raises concerns for deployment in high-stakes domains. To address this issue, we propose Ca2KG, a Causality-aware Calibration framework for KG-RAG. Ca2KG integrates counterfactual prompting, which exposes retrieval-dependent uncertainties in knowledge quality and reasoning reliability, with a panel-based re-scoring mechanism that stabilises predictions across interventions. Extensive experiments on two complex QA datasets demonstrate that Ca2KG consistently improves calibration while maintaining or even enhancing predictive accuracy.

📄 PDF Abstract BibTeX arXiv:2601.09241

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

Simulations evaluating resampling methods for causal discovery: ensemble performance and calibration

2019-10-04 · Erich Kummerfeld, Alexander Rix

Causal discovery can be a powerful tool for investigating causality when a system can be observed but is inaccessible to experiments in practice. Despite this, it is rarely used in any scientific or medical fields. One o…

Causal Discovery

TRUST-ESD: A Risk-Calibrated and Governance-Aware AI Framework for Enterprise Strategic Decision Support Under Uncertainty

2026-07-22 · Tian Qiu, Li Yan, Mahabubur Rahman Miraj, Shanqin Yi 외 arxiv

Enterprise strategic decision support requires AI systems that are not only accurate, but also uncertainty-aware, risk-calibrated, explainable, and governance-compliant. This paper proposes TRUST-ESD, a risk-calibrated a…

Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models

2025-07-12 · Anita Kriz, Elizabeth Laura Janes, Xing Shen, Tal Arbel arxiv

Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt desig…

Visual Question AnsweringZero-shot GeneralizationReinforcement LearningPrompt Engineering

Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

2026-05-04 · Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei 외 arxiv

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. Howeve…

Trustworthiness Calibration Framework for Phishing Email Detection Using Large Language Models

2025-11-06 · Daniyal Ganiuly, Assel Smaiyl arxiv

Phishing emails continue to pose a persistent challenge to online communication, exploiting human trust and evading automated filters through realistic language and adaptive tactics. While large language models (LLMs) su…

Text Classification