DPO (Mixture-of-experts routing): superseded — cited as a baseline and beaten by newer methods. 2 paper(s) critique it, 1 beat it on benchmarks — #63 of 1370 most-superseded. Sub-problem: cluster led by Mixtral. Newer alternatives in the same sub-problem include PADD, MESA, PR2, RouteHijack, MASCing.

Mixture-of-experts routing

DPO

Superseded baseline#63 of 1,370 most-superseded

Superseded — cited as a baseline and beaten by newer methods

2 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites DPO as a baseline.

requires explicit human or teacher model judgments to label one response as preferred over another, making them costly and hard to scale

— OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMs

“standard DPO methods are still inherently limited by their reliance on a single, monolithic policy.”

— Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

PADDPADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
Jun 9, 2026
MESAMESA: Improving MoE Safety Alignment via Decentralized Expertise
May 30, 2026
PR2PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
May 29, 2026
RouteHijackRouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
May 1, 2026
MASCingMASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
Apr 30, 2026
F-SOURSparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
Feb 9, 2026
SocialNav-MoESocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning
Dec 15, 2025
OrdMoEOrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMs
Nov 24, 2025
Mix- and MoE-DPOMix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization
Oct 9, 2025