AI Paper Atlas

Research map / Large language models / Alignment and preferences

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

AAAI 2026 · Large language models › Alignment and preferences · approach: Robust and calibrated DPO · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add approximation matching (similarity filtering of reverse-engineered pairs) (ablation)QueryAligner · Natural Questionsaccuracy: 51.01 -> 54.83Improved
add supervised learning stage (ablation)QueryAligner · Natural Questionsaccuracy: 33.52 -> 54.83Improved
add reinforcement learning stage (ablation)QueryAligner · Natural Questionsaccuracy: 51.52 -> 54.83Improved
add CoT to QueryAligner (ablation)QueryAligner (gpt-4o-mini) · Natural Questionsaccuracy: 53.11 -> 54.83Improved
use QueryAligner rewriting vs plain Naive RAGgpt-4o-mini RAG · Natural Questionsaccuracy: 50.69 -> 54.83Improved
use QueryAligner rewriting vs plain Naive RAGLlama-2-13b RAG · HotpotQAaccuracy: 67.90 -> 74.31Improved
use QueryAligner vs Naive RAGgpt-4o-mini RAG · PubMedQAaccuracy: 93.82 -> 95.44Improved
prepend QueryAligner to existing methods (CoT-SC, RaR, RAFT, Self-RAG, Naive RAG)existing RAG methods · Natural Questionsaccuracy: +2.12 averageImproved
train rewriter on one dataset, fine-tune 10% on targetQueryAligner · cross-dataset (HotpotQA to PubMedQA)accuracy vs Naive RAG: -0.27Hurt
train rewriter on another dataset (transfer)QueryAligner · cross-dataset (other bases to NQ/HotpotQA)accuracy vs Naive RAG: +0.36 to +4.44Improved
QueryAligner vs RaR on gpt-4o-mini PubMedQA EMQueryAligner · PubMedQAEM: 92.59 -> 93.81Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy