# DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization

arXiv: https://arxiv.org/abs/2506.02351 · HTML: https://mlsanity.com/paper/2506.02351/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [A Survey on Content-Aware Video Analysis for Sports](https://mlsanity.com/paper/1703.01170/) (2017)
- [Video Highlight Prediction Using Audience Chat Reactions](https://mlsanity.com/paper/1707.08559/) (2017)
- [Leveraging Contextual Cues for Generating Basketball Highlights](https://mlsanity.com/paper/1606.08955/) (2016)
- [SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs](https://mlsanity.com/paper/2402.10979/) (2024)
- [BADGE: BADminton report Generation and Evaluation with LLM](https://mlsanity.com/paper/2406.18116/) (2024)
- [Large Language Models in Sport Science & Medicine: Opportunities, Risks and Considerations](https://mlsanity.com/paper/2305.03851/) (2023)
- [Automated Detection of Sport Highlights from Audio and Video Sources](https://mlsanity.com/paper/2501.16100/) (2025)
- [Towards Extracting Highlights From Recorded Live Videos: An Implicit Crowdsourcing Approach](https://mlsanity.com/paper/1910.12201/) (2019)

## Built on by (most cited first, 4 of 4)

- [TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization](https://mlsanity.com/paper/2603.01169/) (2026)
- [Neural Sabermetrics with World Model: Play-by-play Predictive Modeling with Large Language Model](https://mlsanity.com/paper/2602.07030/) (2026)
- [A Survey of Large Models in Sports](https://mlsanity.com/paper/2608.14377/) (2026)
- [Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights](https://mlsanity.com/paper/2609.20768/) (2026)

## Abstract (arXiv)

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.