Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Chao, Liang, Yijuan, Xuan, Zihao, Wu, Daokuan, Zhang, Wei, Shen, Xiaoyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915556643307520
author Han, Chao
Liang, Yijuan
Xuan, Zihao
Wu, Daokuan
Zhang, Wei
Shen, Xiaoyu
author_facet Han, Chao
Liang, Yijuan
Xuan, Zihao
Wu, Daokuan
Zhang, Wei
Shen, Xiaoyu
contents The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively activating model components per token, existing methods rely on greedy routing--a myopic execute-or-skip mechanism that often leads to irreversible information loss and suboptimal token selection. This paper introduces informed routing, a new paradigm that proactively addresses these issues. The key insight is to assess not only a token's immediate importance but also its recoverability, i.e., how well its transformation can be approximated. To this end, we propose the Lightweight Feature Forecaster (LFF), a small predictive module that estimates a unit's output before routing decisions are made. This enables a flexible execute-or-approximate policy that preserves model fidelity while drastically reducing computation. Extensive experiments on both language modeling and reasoning tasks show that informed routing achieves state-of-the-art efficiency-performance trade-offs across multiple sparsity levels. Notably, even without final LoRA fine-tuning, our method matches or surpasses strong baselines that require full fine-tuning, all while reducing training time by over 50%. The code is available at: https://github.com/EIT-NLP/informed-routing
format Preprint
id arxiv_https___arxiv_org_abs_2510_13831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
Han, Chao
Liang, Yijuan
Xuan, Zihao
Wu, Daokuan
Zhang, Wei
Shen, Xiaoyu
Computation and Language
Artificial Intelligence
The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively activating model components per token, existing methods rely on greedy routing--a myopic execute-or-skip mechanism that often leads to irreversible information loss and suboptimal token selection. This paper introduces informed routing, a new paradigm that proactively addresses these issues. The key insight is to assess not only a token's immediate importance but also its recoverability, i.e., how well its transformation can be approximated. To this end, we propose the Lightweight Feature Forecaster (LFF), a small predictive module that estimates a unit's output before routing decisions are made. This enables a flexible execute-or-approximate policy that preserves model fidelity while drastically reducing computation. Extensive experiments on both language modeling and reasoning tasks show that informed routing achieves state-of-the-art efficiency-performance trade-offs across multiple sparsity levels. Notably, even without final LoRA fine-tuning, our method matches or surpasses strong baselines that require full fine-tuning, all while reducing training time by over 50%. The code is available at: https://github.com/EIT-NLP/informed-routing
title Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.13831