ReCast repairs all-zero groups and uses contrastive updates on strongest positives and hardest negatives to improve RL in generative recommendation, yielding up to 36.6% better Pass@1 with only 4.1% of baseline rollout budget.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.
UniVA unifies value alignment in generative recommendation via a Commercial SID tokenizer, eCPM-aware RL decoder, and personalized beam search, reporting 37% offline Hit Rate gains and 1.5% online GMV lift on Tencent WeChat Channels.
citing papers explorer
-
ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation
ReCast repairs all-zero groups and uses contrastive updates on strongest positives and hardest negatives to improve RL in generative recommendation, yielding up to 36.6% better Pass@1 with only 4.1% of baseline rollout budget.
-
Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.
-
Unified Value Alignment for Generative Recommendation in Industrial Advertising
UniVA unifies value alignment in generative recommendation via a Commercial SID tokenizer, eCPM-aware RL decoder, and personalized beam search, reporting 37% offline Hit Rate gains and 1.5% online GMV lift on Tencent WeChat Channels.