Pith. sign in

REVIEW 4 cited by

RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.19886 v1 pith:XJNMAQLZ submitted 2024-09-30 cs.LG cs.AIcs.CL

Shuhao Chen , Weisen Jiang , Baijiong Lin , James T. Kwok , Yu Zhang This is my paper
classification cs.LGcs.AIcs.CL
keywords routerdcllmsassemblingcontrastivelearningmodelsrouterrouting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model consists of an encoder and LLM embeddings, and we propose two contrastive learning losses to train the RouterDC model. Experimental results show that RouterDC is effective in assembling LLMs and largely outperforms individual top-performing LLMs as well as existing routing methods on both in-distribution (+2.76\%) and out-of-distribution (+1.90\%) tasks. Source code is available at https://github.com/shuhao02/RouterDC.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compet...

  2. The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.

  3. Orchestration for Domain-specific Edge-Cloud Language Models

    cs.DB 2025-07 conditional novelty 6.0 of 10

    ECO-LLM jointly selects query processing, retrieval, and model components per query, cutting cost by 60% and latency up to 6x versus model routing in edge-cloud tests.

  4. vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models

    cs.NI 2026-02 conditional novelty 5.0 of 10

    vLLM Semantic Router routes LLM requests by composing thirteen signal types into Boolean decision policies, with safety, caching, and model-selection plugin chains.

Pith tools