https://minghuichen.com/categories/acl/ Recent content in ACL on Minghui Chen Hugo en Wed, 01 Jul 2026 00:00:00 +0000 https://minghuichen.com/publication/acl_2026_forvalue/ Wed, 01 Jul 2026 00:00:00 +0000 https://minghuichen.com/publication/acl_2026_forvalue/ <p><strong>Authors:</strong> Wenlong Deng, Qi Zeng, Jiaming Zhang, <strong>Minghui Chen</strong>, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li</p> <p><strong>Published in:</strong> Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers (<strong>ACL 2026</strong>), July 2026, pp. 14581–14600</p> <h2 id="overview">Overview <a href="#overview"><svg class="anchor-symbol" aria-hidden="true" height="26" width="26" viewBox="0 0 22 22" xmlns="http://www.w3.org/2000/svg"> <path d="M0 0h24v24H0z" fill="currentColor"></path> <path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76.0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71.0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71.0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76.0 5-2.24 5-5s-2.24-5-5-5z"></path> </svg></a> </h2> <p>For-Value estimates data influence using final-layer representations and prediction errors. A closed-form calculation replaces backpropagation, allowing examples to be evaluated in batches with a single forward pass. The paper evaluates the method on influential-data detection and mislabeled-data identification for language and vision-language models.</p>