Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Low-Hallucination and Efficient Coreference Resolution with LLMs

Title: Low-Hallucination and Efficient Coreference Resolution with LLMs
Authors: Gan, Yujian; Liang, Yuan; Xie, Jinxia; Lin, Yanni; Yu, Juntao; Poesio, Massimo; Sub Natural Language Processing; Christodoulopoulos, Christos; Chakraborty, Tanmoy; Rose, Carolyn; Peng, Violet
Publication Year: 2025
Subject Terms: Computational Theory and Mathematics; Computer Science Applications; Information Systems; Linguistics and Language
Description: Large Language Models (LLMs) have shown promising results in coreference resolution, especially after fine-tuning. However, recent generative approaches face a critical issue: hallucinations—where the model generates content not present in the original input. These hallucinations make evaluation difficult and decrease overall performance. To address this issue, we analyze the underlying causes of hallucinations and propose a low-hallucination and efficient solution. Specifically, we introduce Efficient Constrained Decoding for Coreference Resolution, which maintains strong robustness while significantly improving computational efficiency.
Document Type: book part
File Description: application/pdf
Language: English
Relation: https://dspace.library.uu.nl/handle/1874/483472
Availability: https://dspace.library.uu.nl/handle/1874/483472
Rights: info:eu-repo/semantics/OpenAccess
Accession Number: edsbas.BDCAD77A
Database: BASE