RAG Optimization Techniques Paper Venue RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis EMNLP'25 SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation EMNLP'25 TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP'25 MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search EMNLP'25 OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Question Answering EMNLP'25 RTTC: Reward-Guided Collaborative Test-Time Compute EMNLP'25 Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs EMNLP'25 Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models EMNLP'25 LLM-Based Dialogue Labeling for Multiturn Adaptive RAG EMNLP'25 EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation ACL'25 ROSERAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization ACL'25 HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation ACL'25 UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation ACL'25 Luna: A Lightweight Evaluation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost COLING'25