IAP uses RL to train LLMs to explicitly infer and apply implicit user intent in single-turn personalized QA, achieving ~7.5% average macro-score gains over baselines on LaMP-QA.
and Chen, Minmin , title =
3 Pith papers cite this work, alongside 9 external citations. Polarity classification is still indexing.
3
Pith papers citing it
9
external citations · external index
years
2026 3representative citing papers
β*-IPS, the optimal additive control-variate estimator, asymptotically dominates SNIPS in MSE; the exact variance gap is (V(π)σ²_w − σ_{w,wr})²/(nσ²_w).
citing papers explorer
-
Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering
IAP uses RL to train LLMs to explicitly infer and apply implicit user intent in single-turn personalized QA, achieving ~7.5% average macro-score gains over baselines on LaMP-QA.
-
Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation
β*-IPS, the optimal additive control-variate estimator, asymptotically dominates SNIPS in MSE; the exact variance gap is (V(π)σ²_w − σ_{w,wr})²/(nσ²_w).
- A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods