Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Linfeng, Zhang, Qinggang, Bi, Baolong, Zeng, Bo, Yuan, Zheng, Chen, Zerui, Wei, Zhimin, Liu, Shenghua, Xu, Linlong, Wang, Longyue, Luo, Weihua, Su, Jinsong
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
par: Chen, Zerui, et autres
Publié: (2026)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
par: Zhang, Qinggang, et autres
Publié: (2025)

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
par: Wu, Chuanjie, et autres
Publié: (2026)

Beyond Single-Reward: Multi-Pair, Multi-Perspective Preference Optimization for Machine Translation
par: Wang, Hao, et autres
Publié: (2025)

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
par: Yao, Jiayu, et autres
Publié: (2025)

Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
par: Chen, Juan, et autres
Publié: (2025)

LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
par: Yu, Zhe, et autres
Publié: (2026)

When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
par: Xiang, Zhishang, et autres
Publié: (2025)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
par: Bi, Baolong, et autres
Publié: (2024)

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
par: Wang, Shaobo, et autres
Publié: (2024)

A State-Transition Framework for Efficient LLM Reasoning
par: Zhang, Liang, et autres
Publié: (2026)

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
par: Mei, Lingrui, et autres
Publié: (2024)

SLANG: New Concept Comprehension of Large Language Models
par: Mei, Lingrui, et autres
Publié: (2024)

LPNL: Scalable Link Prediction with Large Language Models
par: Bi, Baolong, et autres
Publié: (2024)

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
par: Xu, Zhichao, et autres
Publié: (2025)

Challenging Multilingual LLMs: A New Taxonomy and Benchmark for Unraveling Hallucination in Translation
par: Wu, Xinwei, et autres
Publié: (2025)

Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation
par: Cao, Jiajun, et autres
Publié: (2025)

Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
par: Yang, Yonghan, et autres
Publié: (2026)

Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models
par: Liu, Bingshuai, et autres
Publié: (2023)

AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
par: Tong, Siqian, et autres
Publié: (2026)

Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation
par: Xiao, Meiman, et autres
Publié: (2026)

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
par: Chang, Shuochen, et autres
Publié: (2026)

a1: Steep Test-time Scaling Law via Environment Augmented Generation
par: Mei, Lingrui, et autres
Publié: (2025)

Vbox: Efficient Black-Box Serializability Verification
par: Sun, Weihua, et autres
Publié: (2025)

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models
par: Xu, Yilong, et autres
Publié: (2025)

(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts
par: Wu, Minghao, et autres
Publié: (2024)

Context-DPO: Aligning Language Models for Context-Faithfulness
par: Bi, Baolong, et autres
Publié: (2024)

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
par: Wu, Xinwei, et autres
Publié: (2026)

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
par: Mei, Lingrui, et autres
Publié: (2024)

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
par: Bi, Baolong, et autres
Publié: (2024)

HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy
par: Ma, Guoqi, et autres
Publié: (2026)

Difficulty-Estimated Policy Optimization
par: Zhao, Yu, et autres
Publié: (2026)

Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
par: Dong, Su, et autres
Publié: (2026)

Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
par: Hui, Yulong, et autres
Publié: (2025)

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
par: Shi, Ling, et autres
Publié: (2026)

On the Information Redundancy in Non-Autoregressive Translation
par: Wang, Zhihao, et autres
Publié: (2024)

Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models
par: Gao, Linfeng, et autres
Publié: (2025)

Response Enhanced Semi-supervised Dialogue Query Generation
par: Huang, Jianheng, et autres
Publié: (2023)

Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data
par: Su, Yiheng, et autres
Publié: (2023)

Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
par: Ge, Yuyao, et autres
Publié: (2025)