@inproceedings{yang-etal-2026-g,
title = "{G}-Cap: A Game Character Caption Generator",
author = "Yang, Yang and
Hu, Feng and
Zhang, Haiming and
Cheng, XU and
Zheng, Gui and
Yao, Liang and
Ren, Wenqi",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.248/",
pages = "5455--5473",
ISBN = "979-8-89176-390-6",
abstract = "While Large Vision-Language Models (LVLMs) have demonstrated remarkable proficiency in image captioning, existing research primarily focuses on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world scenarios significantly underexplored. In this work, we introduce \textbf{Game Character Captioning}, a novel task designed to evaluate LVLMs' capability to perceive and describe game character from the virtual-world. To facilitate evaluation, we establish \textbf{GC-Bench}, a manually annotated benchmark, and propose \textbf{Graph-F1} to effectively assess performance on this task. Our evaluation reveals that: (1) current state-of-the-art LVLMs, including closed-source giants such as Gemini 3 Pro and GPT-5.1, struggle to maintain the high performance seen in real-world scenarios; and (2) a notable gap exists between open-source and closed-source models. To bridge this gap, we construct \textbf{GC-148K}, a large-scale dataset generated via a specialized data pipeline, and develop the \textbf{G-Cap} series. Experiments demonstrate that G-Cap series rivals the performance of advanced closed-source models at a lower cost, offering an efficient solution for industrial-grade production environment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-g">
<titleInfo>
<title>G-Cap: A Game Character Caption Generator</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">X</namePart>
<namePart type="given">U</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gui</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqi</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>While Large Vision-Language Models (LVLMs) have demonstrated remarkable proficiency in image captioning, existing research primarily focuses on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world scenarios significantly underexplored. In this work, we introduce Game Character Captioning, a novel task designed to evaluate LVLMs’ capability to perceive and describe game character from the virtual-world. To facilitate evaluation, we establish GC-Bench, a manually annotated benchmark, and propose Graph-F1 to effectively assess performance on this task. Our evaluation reveals that: (1) current state-of-the-art LVLMs, including closed-source giants such as Gemini 3 Pro and GPT-5.1, struggle to maintain the high performance seen in real-world scenarios; and (2) a notable gap exists between open-source and closed-source models. To bridge this gap, we construct GC-148K, a large-scale dataset generated via a specialized data pipeline, and develop the G-Cap series. Experiments demonstrate that G-Cap series rivals the performance of advanced closed-source models at a lower cost, offering an efficient solution for industrial-grade production environment.</abstract>
<identifier type="citekey">yang-etal-2026-g</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.248/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>5455</start>
<end>5473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T G-Cap: A Game Character Caption Generator
%A Yang, Yang
%A Hu, Feng
%A Zhang, Haiming
%A Cheng, X. U.
%A Zheng, Gui
%A Yao, Liang
%A Ren, Wenqi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F yang-etal-2026-g
%X While Large Vision-Language Models (LVLMs) have demonstrated remarkable proficiency in image captioning, existing research primarily focuses on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world scenarios significantly underexplored. In this work, we introduce Game Character Captioning, a novel task designed to evaluate LVLMs’ capability to perceive and describe game character from the virtual-world. To facilitate evaluation, we establish GC-Bench, a manually annotated benchmark, and propose Graph-F1 to effectively assess performance on this task. Our evaluation reveals that: (1) current state-of-the-art LVLMs, including closed-source giants such as Gemini 3 Pro and GPT-5.1, struggle to maintain the high performance seen in real-world scenarios; and (2) a notable gap exists between open-source and closed-source models. To bridge this gap, we construct GC-148K, a large-scale dataset generated via a specialized data pipeline, and develop the G-Cap series. Experiments demonstrate that G-Cap series rivals the performance of advanced closed-source models at a lower cost, offering an efficient solution for industrial-grade production environment.
%U https://aclanthology.org/2026.acl-long.248/
%P 5455-5473
Markdown (Informal)
[G-Cap: A Game Character Caption Generator](https://aclanthology.org/2026.acl-long.248/) (Yang et al., ACL 2026)
ACL
- Yang Yang, Feng Hu, Haiming Zhang, XU Cheng, Gui Zheng, Liang Yao, and Wenqi Ren. 2026. G-Cap: A Game Character Caption Generator. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5455–5473, San Diego, California, United States. Association for Computational Linguistics.