<?xml version="1.0" encoding="US-ASCII"?>
<dblp>
<inproceedings key="conf/emnlp/HuaTGGWQ25" mdate="2026-02-02">
<author>Andong Hua</author>
<author>Kenan Tang</author>
<author>Chenhe Gu</author>
<author>Jindong Gu</author>
<author>Eric Wong 0001</author>
<author>Yao Qin 0001</author>
<title>Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs.</title>
<pages>19889-19899</pages>
<year>2025</year>
<booktitle>EMNLP</booktitle>
<ee type="oa">https://doi.org/10.18653/v1/2025.emnlp-main.1006</ee>
<crossref>conf/emnlp/2025</crossref>
<url>db/conf/emnlp/emnlp2025.html#HuaTGGWQ25</url>
<stream>streams/conf/emnlp</stream>
</inproceedings>
</dblp>
