paper-with-me

Papers

InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation

2026-02-09 · Yifan Yang, Jinjia Li, Kunxi Li, Puhao Zheng, Yuanyi Wang, Zheyan Qu, Yang Yu, Jianmin Wu, Ming Li, Hongxia Yang arxiv

The rapid advancement of large language models (LLMs) demands increasingly reliable evaluation, yet current centralized evaluation suffers from opacity, overfitting, and hardware-induced variance. Our empirical analysis reveals an alarming inconsistency in existing evaluations: the standard deviation across ten repeated runs of a single model on HumanEval (1.67) actually exceeds the performance gap among the top-10 models on the official leaderboard (0.91), rendering current rankings statistically precarious. To mitigate these instabilities, we propose a decentralized evaluation framework that enables hardware and parameter diversity through large-scale benchmarking across heterogeneous compute nodes. By leveraging the blockchain-based protocol, the framework incentivizes global contributors to act as independent validators, using a robust reward system to ensure evaluation integrity and discourage dishonest participation. This collective verification transforms evaluation from a "centralized black box" into a "decentralized endorsement" where multi-party consensus and diverse inference environments yield a more stable, representative metric. Experimental results demonstrate that the decentralized evaluation framework reduces the standard deviation across ten runs on the same model to 0.28. This significant improvement over conventional frameworks ensures higher statistical confidence in model rankings. We have completely implemented this platform and will soon release it to the community.

📄 PDF Abstract BibTeX arXiv:2602.08229

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AutoDFL: A Scalable and Automated Reputation-Aware Decentralized Federated Learning

2025-01-08 · Meryem Malak Dif, Mouhamed Amine Bouchiha, Mourad Rabah, Yacine Ghamri-Doudane

Blockchained federated learning (BFL) combines the concepts of federated learning and blockchain technology to enhance privacy, security, and transparency in collaborative machine learning models. However, implementing B…

Federated Learning

Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learning

2024-03-28 · Ji Liu, Chunlu Chen, Yu Li, Lin Sun 외

While centralized servers pose a risk of being a single point of failure, decentralized approaches like blockchain offer a compelling solution by implementing a consensus mechanism among multiple entities. Merging distri…

Distributed ComputingFederated LearningPrivacy Preserving

D2M: A Decentralized, Privacy-Preserving, Incentive-Compatible Data Marketplace for Collaborative Learning

2025-12-11 · Yash Srivastava, Shalin Jain, Sneha Awathare, Nitin Awathare arxiv

The rising demand for collaborative machine learning and data analytics calls for secure and decentralized data sharing frameworks that balance privacy, trust, and incentives. Existing approaches, including federated lea…

Federated Learning

Decentralized Energy Marketplace via NFTs and AI-based Agents

2023-11-17 · Rasoul Nikbakht, Farhana Javed, Farhad Rezazadeh, Nikolaos Bartzoudis 외

The paper introduces an advanced Decentralized Energy Marketplace (DEM) integrating blockchain technology and artificial intelligence to manage energy exchanges among smart homes with energy storage systems. The proposed…

Deep Reinforcement Learningenergy managementenergy tradingManagement

A Differentially Private Blockchain-Based Approach for Vertical Federated Learning

2024-07-09 · Linh Tran, Sanjay Chari, Md. Saikat Islam Khan, Aaron Zachariah 외

We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to a…

Federated LearningVertical Federated Learning