Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Amirizaniani, Maryam, Lee, Benjamin Charles Germain, West, Jevin, Weber, Nicholas
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.12645
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916006769721344
author Amirizaniani, Maryam
Lee, Benjamin Charles Germain
West, Jevin
Weber, Nicholas
author_facet Amirizaniani, Maryam
Lee, Benjamin Charles Germain
West, Jevin
Weber, Nicholas
contents Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers to the implicit ``why'' behind a query beyond its explicit wording. However, existing approaches to intent-aware personalization rely on multi-turn conversational context or rich user profiles, and do not explicitly model user intent during the reasoning process. This limits their effectiveness in single-turn settings, where the user's latent goal must be inferred from minimal input and integrated into the thinking and reasoning process. To bridge this gap, we propose IAP (Intent-Aware Personalization), a reinforcement learning framework that trains models to infer implicit user intent directly from a single-turn question and incorporate it into thinking steps through a tag-based schema for generating personalized, intent-grounded answers. By optimizing intent-aware answer trajectories under a personalized reward function, IAP reinforces generation paths that make implicit user intent explicit and produce responses that better align with the user's underlying goal. Through experiments on the LaMP-QA benchmark across six models, IAP consistently outperforms all baselines, achieving an average macro-score gain of around 7.5\% over the strongest competitor, demonstrating that modeling implicit user intent within the training objective is a promising direction for PQA.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12645
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering
Amirizaniani, Maryam
Lee, Benjamin Charles Germain
West, Jevin
Weber, Nicholas
Computation and Language
Artificial Intelligence
Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers to the implicit ``why'' behind a query beyond its explicit wording. However, existing approaches to intent-aware personalization rely on multi-turn conversational context or rich user profiles, and do not explicitly model user intent during the reasoning process. This limits their effectiveness in single-turn settings, where the user's latent goal must be inferred from minimal input and integrated into the thinking and reasoning process. To bridge this gap, we propose IAP (Intent-Aware Personalization), a reinforcement learning framework that trains models to infer implicit user intent directly from a single-turn question and incorporate it into thinking steps through a tag-based schema for generating personalized, intent-grounded answers. By optimizing intent-aware answer trajectories under a personalized reward function, IAP reinforces generation paths that make implicit user intent explicit and produce responses that better align with the user's underlying goal. Through experiments on the LaMP-QA benchmark across six models, IAP consistently outperforms all baselines, achieving an average macro-score gain of around 7.5\% over the strongest competitor, demonstrating that modeling implicit user intent within the training objective is a promising direction for PQA.
title Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.12645