LinkModel: uncertainty-guided hybrid inference between small and large language models for out-of-distribution generalization

Large language models (LLMs) exhibit strong generalization capability, but their inference cost is high and they are not always superior on supervised tasks to locally deployed small language models (SLMs) fine-tuned on labeled data. In contrast, SLMs can achieve strong in-domain performance with efficient deployment, yet often degrade under out-of-distribution (OOD) or cross-domain shifts. Although prior work has studied hybrid inference that invokes LLMs on demand, most approaches rely on trained routers and are primarily designed for generative tasks; under supervised classification with the ID-to-OOD transfer setting, stable and interpretable collaboration without additional router training remains underexplored. To this end, we propose LinkModel, an uncertainty-guided hybrid inference framework. LinkModel follows a Prediction–Estimation–Prediction mechanism: a locally fine-tuned SLM first produces a prediction and estimates uncertainty to obtain a risk signal, and a threshold-gated policy then defers high-risk samples to an LLM for a second-pass prediction. This design improves accuracy and robustness while controlling the LLM invocation ratio and the overall cost. We conduct systematic evaluation and mechanism analysis under the GLUE-X OOD generalization setting; results show that LinkModel achieves consistent end-to-end gains across multiple train–test transfer combinations and substantially mitigates OOD performance degradation.

Authors

Institutions

Publication Details

Journal
Complex & Intelligent Systems
Published
2026-11-16
DOI
https://doi.org/10.1007/s40747-026-02583-y
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

LinkModel: uncertainty-guided hybrid inference between small and large language models for out-of-distribution generalization

Wentao Bai, Yue Qin Cao, Fan Guo, Jiale Song
2 links
Complex & Intelligent Systems
Topic Modeling
article

LinkModel: uncertainty-guided hybrid inference between small and large language models for out-of-distribution generalization

Wentao Bai, Yue Qin Cao, Fan Guo, Jiale Song
article en

Abstract

Large language models (LLMs) exhibit strong generalization capability, but their inference cost is high and they are not always superior on supervised tasks to locally deployed small language models (SLMs) fine-tuned on labeled data. In contrast, SLMs can achieve strong in-domain performance with efficient deployment, yet often degrade under out-of-distribution (OOD) or cross-domain shifts. Although prior work has studied hybrid inference that invokes LLMs on demand, most approaches rely on trained routers and are primarily designed for generative tasks; under supervised classification with the ID-to-OOD transfer setting, stable and interpretable collaboration without additional router training remains underexplored. To this end, we propose LinkModel, an uncertainty-guided hybrid inference framework. LinkModel follows a Prediction–Estimation–Prediction mechanism: a locally fine-tuned SLM first produces a prediction and estimates uncertainty to obtain a risk signal, and a threshold-gated policy then defers high-risk samples to an LLM for a second-pass prediction. This design improves accuracy and robustness while controlling the LLM invocation ratio and the overall cost. We conduct systematic evaluation and mechanism analysis under the GLUE-X OOD generalization setting; results show that LinkModel achieves consistent end-to-end gains across multiple train–test transfer combinations and substantially mitigates OOD performance degradation.

Complex & Intelligent Systems
East China University of Science and Technology (CN), Donghua University (CN), Nanjing Institute of Technology (CN), Suzhou Polytechnic Institute of Agriculture (CN), Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education (CN)
Natural Science Research of Jiangsu Higher Education Institutions of China
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon