@inproceedings{kang-etal-2025-diamond,
title = "{DIAMOND}: An {LLM}-Driven Agent for Context-Aware Baseball Highlight Summarization",
author = "Kang, Jeonghun and
Kwon, Soonmok and
Lee, Joonseok and
Kim, Byung-Hak",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Lu, Xing Han and
Dziri, Nouha and
Murty, Shikhar and
Lacoste, Alexandre",
booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.realm-1.28/",
doi = "10.18653/v1/2025.realm-1.28",
pages = "386--400",
ISBN = "979-8-89176-264-0",
abstract = "Highlight summarization in baseball requires balancing statistical analysis with narrative coherence. Traditional approaches{---}such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection{---}can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable.We introduce $\textbf{DIAMOND}$, an $\textbf{LLM-driven agent for context-aware baseball highlight summarization}$ that integrates $\textbf{structured sports analytics with natural language reasoning}$. DIAMOND leverages sabermetric features{---}Win Expectancy, WPA, and Leverage Index{---}to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both $\textbf{quantitative rigor and qualitative richness}$, surpassing the limitations of purely statistical or vision-based systems.Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9{\%} (WPA-only) to 84.8{\%}, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2025-diamond">
<titleInfo>
<title>DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeonghun</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soonmok</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonseok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byung-Hak</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Murty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Lacoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-264-0</identifier>
</relatedItem>
<abstract>Highlight summarization in baseball requires balancing statistical analysis with narrative coherence. Traditional approaches—such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection—can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable.We introduce DIAMOND, an LLM-driven agent for context-aware baseball highlight summarization that integrates structured sports analytics with natural language reasoning. DIAMOND leverages sabermetric features—Win Expectancy, WPA, and Leverage Index—to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both quantitative rigor and qualitative richness, surpassing the limitations of purely statistical or vision-based systems.Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9% (WPA-only) to 84.8%, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond.</abstract>
<identifier type="citekey">kang-etal-2025-diamond</identifier>
<identifier type="doi">10.18653/v1/2025.realm-1.28</identifier>
<location>
<url>https://aclanthology.org/2025.realm-1.28/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>386</start>
<end>400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization
%A Kang, Jeonghun
%A Kwon, Soonmok
%A Lee, Joonseok
%A Kim, Byung-Hak
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Lu, Xing Han
%Y Dziri, Nouha
%Y Murty, Shikhar
%Y Lacoste, Alexandre
%S Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-264-0
%F kang-etal-2025-diamond
%X Highlight summarization in baseball requires balancing statistical analysis with narrative coherence. Traditional approaches—such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection—can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable.We introduce DIAMOND, an LLM-driven agent for context-aware baseball highlight summarization that integrates structured sports analytics with natural language reasoning. DIAMOND leverages sabermetric features—Win Expectancy, WPA, and Leverage Index—to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both quantitative rigor and qualitative richness, surpassing the limitations of purely statistical or vision-based systems.Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9% (WPA-only) to 84.8%, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond.
%R 10.18653/v1/2025.realm-1.28
%U https://aclanthology.org/2025.realm-1.28/
%U https://doi.org/10.18653/v1/2025.realm-1.28
%P 386-400
Markdown (Informal)
[DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization](https://aclanthology.org/2025.realm-1.28/) (Kang et al., REALM 2025)
ACL