Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning

• URL: http://arxiv.org/abs/2603.03752v1
• Date: Wed, 04 Mar 2026 05:55:20 GMT
• Title: Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
• Authors: Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Xavier Wang, Yaxiao Liu,
• Abstract summary: Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs)<n>We propose COllaborative REAsoner (COREA) to achieve a balance between accuracy and cost in complex reasoning tasks.
• Score: 9.317710715121793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a system that cascades an SLM with an LLM to achieve a balance between accuracy and cost in complex reasoning tasks. COREA first attempts to answer questions using the SLM, which outputs both an answer and a verbalized confidence score. Questions with confidence below a predefined threshold are deferred to the LLM for more accurate resolution. We introduce a reinforcement learning-based training algorithm that aligns the SLM's confidence through an additional confidence calibration reward. Extensive experiments demonstrate that our method jointly improves the SLM's reasoning ability and confidence calibration across diverse datasets and model backbones. Compared to using the LLM alone, COREA reduces cost by 21.5% and 16.8% on out-of-domain math and non-math datasets, respectively, with only an absolute pass@1 drop within 2%.

Related papers

• On Calibration of Large Language Models: From Response To Capability [66.59139960234326]
  Large language models (LLMs) are widely deployed as general-purpose problem solvers.<n>We introduce capability calibration, which targets the model's expected accuracy on a query.<n>Our results demonstrate that capability-calibrated confidence improves pass@$k$ prediction and inference budget allocation.
  arXiv  Detail & Related papers  (2026-02-14T01:07:45Z)
• Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference [7.865726406769634]
  Small Language Models (SLMs) offer dramatic cost savings yet lag substantially in accuracy.<n>We introduce LLM Shepherding, a framework that requests only a short prefix (a hint) from the LLM and provides it to SLM.<n>Shepherding generalizes both routing and cascading, and it achieves lower cost under oracle decision-making.
  arXiv  Detail & Related papers  (2026-01-29T18:52:54Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• LLM-Powered Preference Elicitation in Combinatorial Assignment [17.367432304040662]
  We study the potential of large language models (LLMs) as proxies for humans to simplify preference elicitation (PE) in assignment.<n>We propose a framework for LLM proxies that can work in tandem with SOTA ML-powered preference elicitation schemes.<n>We experimentally evaluate the efficiency of LLM proxies against human queries in the well-studied course allocation domain.
  arXiv  Detail & Related papers  (2025-02-14T17:12:20Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs [74.35290684163718]
  A primary challenge in large language model (LLM) development is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by leveraging a small language model (SLM)
  arXiv  Detail & Related papers  (2024-10-24T14:31:52Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models [10.684722193666607]
  We introduce REQUAL-LM, a novel method for finding reliable and equitable large language models (LLMs) outputs through aggregation. Specifically, we develop a Monte Carlo method based on repeated sampling to find a reliable output close to the mean of the underlying distribution of possible outputs. We formally define the terms such as reliability and bias, and design an equity-aware aggregation to minimize harmful bias while finding a highly reliable output.
  arXiv  Detail & Related papers  (2024-04-17T22:12:41Z)
• Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs [60.61002524947733]
  Previous confidence elicitation methods rely on white-box access to internal model information or model fine-tuning. This leads to a growing need to explore the untapped area of black-box approaches for uncertainty estimation. We define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
  arXiv  Detail & Related papers  (2023-06-22T17:31:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.