QueryAligner: Customizing User Query to Match LLMs Preferences for Better Intent Recognition
Yunlong Ma, Bo Wang, Yihong Tang, Zifei Yu, Chenyun Xue, Gaoke Zhang, Yuexian Hou
Abstract
The interpretative efficacy of large language models (LLMs) fundamentally hinges on the intricate alignment between user inputs and model-specific linguistic priors. Existing methodologies predominantly employ static input optimization strategies, failing to account for the empirically observed divergence in linguistic preference spaces across distinct LLM architectures, including variations in syntactic parsing heuristics, semantic grounding mechanisms, and knowledge retrieval pathways. We propose QueryAligner, an adaptive rewriting system implementing dynamic model-aware input transformation through architecture-specific preference modeling. Our framework introduces two pivotal innovations: 1) A dual-phase optimization engine integrating supervised learning on reverse-engineered cross-architectural training data with reinforcement learning driven by multi-objective reward signals, ensuring simultaneous preservation of semantic integrity and maximization of target model compatibility; 2) An architecture-informed rewriting protocol that automatically discovers latent alignment patterns encoded within distinct LLMs
BibTeX
@inproceedings{aaai2026_queryalignercust,
title = {QueryAligner: Customizing User Query to Match LLMs Preferences for Better Intent Recognition},
author = {Yunlong Ma and Bo Wang and Yihong Tang and Zifei Yu and Chenyun Xue and Gaoke Zhang and Yuexian Hou},
booktitle = {AAAI 2026},
year = {2026}
}