Copertina

Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Li, Yang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

kNN-Graph: An adaptive graph model for $k$-nearest neighbors
di: Li, Jiaye, et al.
Pubblicazione: (2026)

Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spaces
di: Lugosi, Gábor, et al.
Pubblicazione: (2025)

kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech
di: Hajal, Karl El, et al.
Pubblicazione: (2024)

LLM Router: Rethinking Routing with Prefill Activations
di: Varshney, Tanay, et al.
Pubblicazione: (2026)

kNN Classification of Malware Data Dependency Graph Features
di: Musgrave, John, et al.
Pubblicazione: (2024)

TRAKNN: Efficient Trajectory Aware Spatiotemporal kNN for Rare Meteorological Trajectory Detection
di: Coulaud, Guillaume, et al.
Pubblicazione: (2026)

C-kNN-LSH: A Nearest-Neighbor Algorithm for Sequential Counterfactual Inference
di: Wang, Jing, et al.
Pubblicazione: (2026)

Optimizing Parallel Schemes with Lyapunov Exponents and kNN-LLE Estimation
di: Shams, Mudassir, et al.
Pubblicazione: (2026)

Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification
di: Doerrich, Sebastian, et al.
Pubblicazione: (2024)

Improved convergence rate of kNN graph Laplacians: differentiable self-tuned affinity
di: Cheng, Xiuyuan, et al.
Pubblicazione: (2024)

Exploring the Limitations of kNN Noisy Feature Detection and Recovery for Self-Driving Labs
di: Shi, Qiuyu, et al.
Pubblicazione: (2025)

ICL-Router: In-Context Learned Model Representations for LLM Routing
di: Wang, Chenxu, et al.
Pubblicazione: (2025)

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
di: Gui, Zhongrui, et al.
Pubblicazione: (2024)

SkillRouter: Skill Routing for LLM Agents at Scale
di: Zheng, YanZhao, et al.
Pubblicazione: (2026)

SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN
di: Mariotti, Luca, et al.
Pubblicazione: (2025)

This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN
di: Tang, Dennis, et al.
Pubblicazione: (2025)

RouterBench: A Benchmark for Multi-LLM Routing System
di: Hu, Qitian Jason, et al.
Pubblicazione: (2024)

kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization
di: Shao, Keren, et al.
Pubblicazione: (2025)

PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
di: Dai, Zhongjie, et al.
Pubblicazione: (2025)

k-NN as a Simple and Effective Estimator of Transferability
di: Sorkhei, Moein, et al.
Pubblicazione: (2025)

Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts
di: Lyu, Boxuan, et al.
Pubblicazione: (2026)

RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
di: Lu, Yifan, et al.
Pubblicazione: (2025)

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
di: Patel, Shivam, et al.
Pubblicazione: (2025)

MasRouter: Learning to Route LLMs for Multi-Agent Systems
di: Yue, Yanwei, et al.
Pubblicazione: (2025)

Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
di: Askin, Baris, et al.
Pubblicazione: (2026)

Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
di: Zhang, Yichi, et al.
Pubblicazione: (2025)

HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning
di: Gupta, Nikunj, et al.
Pubblicazione: (2025)

Optimizing $k$ in $k$NN Graphs with Graph Learning Perspective
di: Tamaru, Asuka, et al.
Pubblicazione: (2024)

Rerouting LLM Routers
di: Shafran, Avital, et al.
Pubblicazione: (2025)

Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
di: Huang, Hai, et al.
Pubblicazione: (2026)

VL-RouterBench: A Benchmark for Vision-Language Model Routing
di: Huang, Zhehao, et al.
Pubblicazione: (2025)

OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learning
di: Bao, Zhenghua, et al.
Pubblicazione: (2026)

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
di: Tang, Haochun, et al.
Pubblicazione: (2026)

Embedding Graphs as Euclidean kNN-Graphs
di: Schibler, T., et al.
Pubblicazione: (2025)

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
di: Stripelis, Dimitris, et al.
Pubblicazione: (2024)

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models
di: Wu, Hang, et al.
Pubblicazione: (2025)

LogRouter: Adaptive Two-Level LLM Routing for Log Question Answering in Big Data Systems
di: Coskuner, Mert, et al.
Pubblicazione: (2026)

Surprisal Driven $k$-NN for Robust and Interpretable Nonparametric Learning
di: Banerjee, Amartya, et al.
Pubblicazione: (2023)

Lodestar: An Online-Learning LLM Inference Router
di: Lim, Gangmuk, et al.
Pubblicazione: (2026)

HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models
di: Basu, Abhinaba
Pubblicazione: (2026)