Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference

TL;DR

This paper introduces a cost-aware Proof of Quality framework for decentralized LLM inference, integrating efficiency metrics into the verification process to promote high-quality, cost-effective AI model evaluation.

Contribution

It proposes a novel cost-aware PoQ design that incorporates explicit efficiency measurements and a unified evaluation pipeline, improving scalability and economic sustainability.

Findings

Bi encoder correlates better with ground truth and GPT scores.

Largest models are most efficient per unit latency.

Cost-aware reward scheme favors high quality, low cost nodes.

Abstract

Decentralized large language model (LLM) inference promises transparent and censorship resistant access to advanced AI, yet existing verification approaches struggle to scale to modern models. Proof of Quality (PoQ) replaces cryptographic verification of computation with consensus over output quality, but the original formulation ignores heterogeneous computational costs across inference and evaluator nodes. This paper introduces a cost-aware PoQ framework that integrates explicit efficiency measurements into the reward mechanism for both types of nodes. The design combines ground truth token level F1, lightweight learned evaluators, and GPT based judgments within a unified evaluation pipeline, and adopts a linear reward function that balances normalized quality and cost. Experiments on extractive question answering and abstractive summarization use five instruction tuned LLMs ranging from TinyLlama-1.1B to Llama-3.2-3B and three evaluation models spanning cross encoder and bi encoder architectures. Results show that a semantic textual similarity bi encoder achieves much higher correlation with both ground truth and GPT scores than cross encoders, indicating that evaluator architecture is a critical design choice for PoQ. Quality-cost analysis further reveals that the largest models in the pool are also the most efficient in terms of quality per unit latency. Monte Carlo simulations over 5\,000 PoQ rounds demonstrate that the cost-aware reward scheme consistently assigns higher average rewards to high quality low cost inference models and to efficient evaluators, while penalizing slow low quality nodes. These findings suggest that cost-aware PoQ provides a practical foundation for economically sustainable decentralized LLM inference.