Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI

arXiv:2608.20393v1 Announce Type: cross Abstract: Agentic large language models (LLMs) deployed in fact-sensitive applications such as customer support must simultaneously preserve factual correctness and generate responses in a controllable stylistic register. Activation steering enables fine-tuning-free style control by perturbing hidden representations, but it lacks an explicit mechanism for distinguishing verifiable facts from stylistic content, leading to semantic leakage. We address this challenge through Defactualize-Steer-Rehydrate (DSR), a knowledge-engineering framework that integrates a typed, salience-weighted knowledge graph (KG) with activation steering. DSR extracts salient entities using a layered regex or NER or lexical-classifier pipeline, replaces them with typed placeholders prior to steering, and deterministically restores verified values through salience-guided rehydration after generation. DSR is evaluated across six LLaMA-family models (1B--13B parameters) on 600 A2A-generated customer-support cases (1,200 generations), with a dedicated KG ablation study. DSR significantly increases verified-entity recovery relative to a steering-only baseline (Cohen's d=0.225, p_{ext{Bonf}}=1.0imes10^{-4}), though the absolute recovery rate remains modest, while preserving effective style control across diverse model families. Layer-wise separability and steering-strength diagnostics further show previously unexplored interactions between representation-level steering and factual grounding. hese results demonstrate that explicit knowledge engineering can systematically enhance trustworthy, controllable, and reproducible generative AI without requiring model fine-tuning. Code, cached steering vectors, and evaluation scripts are publicly released to support reproducibility.footnote{https://github.com/Tanmay-IITDSAI/KG-Gated-Defactualization}

Related

• Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
• Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
• LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

Source: arXiv cs.AI | 2026-08-24