RL post-training makes generative recommenders better rankers but worse retrievers, study finds

_reachsumit · x · 2026-11-18

A new paper uncovers a hidden cost of RL post-training in generative recommenders: across all five datasets studied, RL improves top-of-list accuracy (hit@K for small K) but lowers candidate-list recall (hit@K for K in the hundreds) — the model becomes a better ranker and a worse retriever, which matters since deployed models hand hundreds of candidates to downstream rankers.

Root cause

Fix

Original post →

More from Research

Research channel →