# kaal:claim:4855607-035

**Claim.** Applying decentralized voting and consensus to RLHF permits human feedback to be verified before it is used to calibrate the Reward Model, which raises the integrity and reliability of the feedback data entering the model.

**Type.** design  **Support.** argued

**Holds when.**

- RLHF pipelines where feedback can be verified prior to reward model training

**Source quote.**

> Applying these mechanisms to RLHF allows for the decentralized verification of human feedback before it's used to calibrate the RM, enhancing the integrity and reliability of the feedback data.

**From.** Wulf A. Kaal, *How AI Models are Optimized Through Web3 Governance* (2024), RLHF Optimization, page 52

**Cite as.** Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024). SSRN: https://ssrn.com/abstract=4855607

**Verify.** sha256 of source PDF `eb0b3e62374b45a8fa888c6bde9725e606bcb46cf4b5e74a6e851d9f25099113` at https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202024%20-%20How%20AI%20Models%20are%20Optimized%20Through%20Web3%20Governance.pdf

**Topics.** decentralization, governance-design

**Keywords.** rlhf, reward-model, feedback-verification, decentralized-voting, data-integrity

**Canonical form.** This markdown file is the canonical hashed representation of the claim. Its sha256 is the content hash used for attestation.