Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Multi-objective RLHF alignment on safeRLHF (test) benchmark leaderboard · SOTA2 Research

Research Benchmarks

Multi-objective RLHF alignment on safeRLHF (test)

52Win RateMAVIS

Updated 5mo ago

Evaluation Results

Method	Links
MAVIS2025.08		52

SOTA Paper

MAVIS

MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection

Dataset

SafeRLHF

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Helpfulness on HH-RLHF (test)Harmlessness on HH-RLHF (test)Humor on HH-RLHF (test)Faithfulness on Summarization (test)