Skip to content

Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressions

Sep 2026 · arXiv.org · Vol abs/2609.34326 · 0 citations · 44 references
Computer Science

TL;DR

RegEXROUTE is introduced, a pipeline that uses sparse autoencoders (SAEs) to discover interpretable regular-expression (regex) features and establishes explicit, interpretable text features as a practical basis for designing and understanding LLM routers.

Abstract

Large Language Model (LLM) routers commonly rely on neural query embeddings, with larger encoders expected to better capture query intent and difficulty. Yet scaling Qwen2.5 encoders from 0.5B to 72B parameters brings little improvement in routing accuracy (Figure 1b), suggesting that small encoders may already capture the query properties needed for routing. We therefore investigate which properties matter and whether they can be extracted directly from text without a neural encoder. We introduce REGEXROUTE, a pipeline that uses sparse autoencoders (SAEs) to discover interpretable regular-expression (regex) features. Using unlabeled text, an LLM turns descriptions of grouped SAE latents into regex extractors and refines them to match latent activation patterns. These extractors supply numerical features to a lightweight routing head, eliminating neural encoding at inference (Figure 1a). Across four benchmarks, one fixed set of 128 features achieves 76.43% average routing accuracy, comparable to 76.41% for the strongest neural text encoder baseline, with much smaller latency and strong robustness. These findings establish explicit, interpretable text features as a practical basis for designing and understanding LLM routers.

View source

Similar papers

Preprint Aug 2026

Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings

This work introduces Giga-Embeddings, a family of text embedding models designed to combine strong retrieval quality with efficient serving, and trains the compact model using a dimension-agnostic objective that aligns teacher and student similarity distributions.

Egor Kolodin, Egor Krasnoperov, Evgeniy Kosarev et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Query-aware routing for Cross-lingual performance gains in Encoders

Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language performance. We investigate whether Finnish and Swedish cross-lingual retrieval can improve while preserving an encoder's existing same-language performance and document...

Akshay Jain, Edward Kim · 0 citations
#machine learning Preprint Aug 2026

Can LLMs Use Relational Transformer Embeddings?

It is argued that soft-token fusion requires stronger alignment objectives and schema-aware design before it can serve as a reliable route to relational prediction.

Francisco Galuppo Azevedo, Clarissa Lima Loures · 0 citations

IMoKGNN: Dual-Stream Fusion of Generic and Task-Specific Language Model Features for Graph Neural Networks

A dual-channel knowledge fusion framework, named MoKGNN, to simultaneously leverage the generic semantic knowledge from LLMs and the task adaptation capability of TLM, and a Knowledge Alignment Network to align the LLM embeddings with the TLM representations.

Hao Yan, Chao-Zhuo Li, Jun Yin et al. · 0 citations
Sep 2026

Resolution as a First-Class Decision: Task-Conditioned Routing for Efficient Multimodal Large Language Models

The inference efficiency of Multimodal Large Language Models (MLLMs) is severely constrained by massive visual token sequences induced by high-resolution inputs, with computational cost scaling quadratically. Existing approaches primarily focus on downstream token compression, while overlooking a fundamental upstream i...

Zhi-Qiang Xia, Yang Li, Xin-Yuan Zhang et al. · 0 citations
#natural language process... Preprint Sep 2026

Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations

Analysis shows that Lngram v2 substantially reduces both total and activated memory parameters while maintaining or improving language modeling performance, and shows that its discrete IDs preserve substantial semantic structure of continuous hidden states, enabling semantic recovery from IDs alone and stable ID--seman...

Yun Zheng, Bin Wen, Xiao-Jie Wang et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.