Lune

ACL Findings2026

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Abstract

Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided context or fail to fully leverage the provided evidence. Existing methods attempt to improve faithfulness through external interventions, such as specialized prompting, decoding-based calibration, or preference optimization. However, since these approaches treat the LLM as a black box, they lack a reliable mechanism to assess when and why knowledge conflicts occur. Consequently, they tend to be brittle, data-intensive, and agnostic to the model's internal reasoning process. In this paper, we move beyond black-box interventions to analyze the model's internal reasoning process. We discover that conflicting and aligned knowledge states are linearly separable in the model's latent space, and contextual noise systematically increases the entropy of these representations. Based on these findings, we propose ProbeRAG, a novel framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model's latent space, and (iii) conflict-aware attention to modulate attention heads toward faithful context integration. Extensive experiments demonstrate that ProbeRAG substantially improves both accuracy and contextual faithfulness. The related resources are available at https://github. com/XMUDeepLIT/ProbeRAG.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented GenerationChuanjie Wu, Zhishang Xiang, Yunbo Tang, Zerui Chen et al.KDD 2026 · 1 citation

Builds on41

  1. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  2. The Linear Representation Hypothesis and the Geometry of Large Language ModelsKiho Park, Yo Joong Choe, Victor VeitchICML 2024 · 461 citations
  3. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language ModelsPotsawee Manakul, Adian Liusie, Mark J. F. GalesEMNLP 2023 · 331 citations
  4. Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsJian Xie, Kai Zhang, Jiangjie Chen, Renze Lou et al.ICLR 2024 · 294 citations
  5. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations

Related papers

  1. FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented GenerationQinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang et al.ACL 2025 · 18 citations
  2. Conflict-Aware RAG: Multi-Stage Learning with Conflict Signals for Robust Retrieval-Augmented GenerationHaiyan Wu, Chenchen Wang, Chaoqun Sun, Chengxiong Lu et al.WWW 2026
  3. Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented GenerationGuanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang et al.WWW 2025 · 44 citations
  4. Understanding Parametric and Contextual Knowledge Reconciliation within Large Language ModelsJun Zhao, Yongzhuo Yang, Xiang Hu, Jingqi Tong et al.NeurIPS 2025 · 10 citations
  5. Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under ConflictsXiaowei Yuan, Ziyang Huang, Zhao Yang, Yequan Wang et al.ACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines