# Trust, but verify

arXiv: https://arxiv.org/abs/2504.13443 · HTML: https://mlsanity.com/paper/2504.13443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [zkLLM: Zero Knowledge Proofs for Large Language Models](https://mlsanity.com/paper/2404.16109/) (2024)
- [Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactions](https://mlsanity.com/paper/2402.06414/) (2024)

## Built on by (most cited first, 2 of 2)

- [CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs](https://mlsanity.com/paper/2505.13778/) (2025)
- [Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation](https://mlsanity.com/paper/2508.00912/) (2025)

## Abstract (arXiv)

Decentralized AI agent networks, such as Gaia, allows individuals to run customized LLMs on their own computers and then provide services to the public. However, in order to maintain service quality, the network must verify that individual nodes are running their designated LLMs. In this paper, we demonstrate that in a cluster of mostly honest nodes, we can detect nodes that run unauthorized or incorrect LLM through social consensus of its peers. We will discuss the algorithm and experimental data from the Gaia network. We will also discuss the intersubjective validation system, implemented as an EigenLayer AVS to introduce financial incentives and penalties to encourage honest behavior from LLM nodes.