Saved in:
Bibliographic Details
Main Authors: Su, Hang, Liu, Zequn, Hu, Chen, Lu, Xuesong, Xia, Yingce, Liu, Zhen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14773
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917413283430400
author Su, Hang
Liu, Zequn
Hu, Chen
Lu, Xuesong
Xia, Yingce
Liu, Zhen
author_facet Su, Hang
Liu, Zequn
Hu, Chen
Lu, Xuesong
Xia, Yingce
Liu, Zhen
contents While LLMs have demonstrated remarkable potential in Question Answering (QA), evaluating personalization remains a critical bottleneck. Existing paradigms predominantly rely on lexical-level similarity or manual heuristics, often lacking sufficient data-driven validation. We address this by mining Community-Individual Preference Divergence (CIPD), where individual choices override consensus, to distill six key personalization factors as evaluative dimensions. Accordingly, we introduce CoPA, a benchmark with 1,985 user profiles for fine-grained, factor-level assessment. By quantifying the alignment between model outputs and user-specific cognitive preferences inferred from interaction patterns, CoPA provides a more comprehensive and discriminative standard for evaluating personalized QA than generic metrics. The code is available at https://github.com/bjzgcai/CoPA.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14773
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors
Su, Hang
Liu, Zequn
Hu, Chen
Lu, Xuesong
Xia, Yingce
Liu, Zhen
Computation and Language
While LLMs have demonstrated remarkable potential in Question Answering (QA), evaluating personalization remains a critical bottleneck. Existing paradigms predominantly rely on lexical-level similarity or manual heuristics, often lacking sufficient data-driven validation. We address this by mining Community-Individual Preference Divergence (CIPD), where individual choices override consensus, to distill six key personalization factors as evaluative dimensions. Accordingly, we introduce CoPA, a benchmark with 1,985 user profiles for fine-grained, factor-level assessment. By quantifying the alignment between model outputs and user-specific cognitive preferences inferred from interaction patterns, CoPA provides a more comprehensive and discriminative standard for evaluating personalized QA than generic metrics. The code is available at https://github.com/bjzgcai/CoPA.
title CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors
topic Computation and Language
url https://arxiv.org/abs/2604.14773