The paper proposes GroundedCache, an evidence-validated cache router that significantly improves the safety of reusing cached semantic answers in RAG systems by requiring multiple gates to validate th…

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

The paper proposes formulating RAG design as an architecture search problem and introduces RAISE, a comprehensive framework and benchmark for systematically optimizing RAG hyperparameters.

HiKEY proposes a hierarchical, tree-based multimodal retrieval framework that significantly improves open-domain document question answering by addressing document routing and evidence fragmentation.

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

OrcaRouter is a production-ready LLM router that uses a hybrid offline-online learning approach to efficiently select the best large language model for an incoming query, achieving high accuracy at lo…

The paper introduces 'Routing Hijacking,' a severe attack where malicious clients forge semantic profiles in Federated RAG systems to misroute target queries, and proposes a trust-aware post-routing f…

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

The paper proposes the Sentinel-Strategist architecture, an adaptive defense mechanism that selectively deploys security measures in Retrieval-Augmented Generation (RAG) systems to significantly reduc…

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

SilentRetrieval introduces a sophisticated, two-stage data poisoning attack that successfully hijacks Retrieval-Augmented Generation (RAG) systems by injecting adversarially crafted, yet highly fluent…

The paper introduces Entity-Collision, a rigorous protocol that separates genuine retrieval lift from simple lexical overlap, demonstrating that embedder performance depends critically on the query ty…

The paper proposes a rigorous, fixed-budget, cluster-aware standard for LLM-as-a-judge evaluation of multi-hop RAG systems, demonstrating that current evaluation methods often overstate performance.

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…

Lodestar is a novel online learning-based request routing system that significantly improves LLM inference efficiency by dynamically assigning incoming requests to the optimal GPU instance to minimize…

GPIR is a GPU-accelerated Private Information Retrieval (PIR) system that significantly boosts throughput by introducing a stage-aware hybrid execution model and optimizing data layouts for modern GPU…

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost…