When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914963912654848 |
|---|---|
| author | Hu, Yebowen Song, Kaiqiang Cho, Sangwoo Wang, Xiaoyang Yao, Wenlin Foroosh, Hassan Yu, Dong Liu, Fei |
| author_facet | Hu, Yebowen Song, Kaiqiang Cho, Sangwoo Wang, Xiaoyang Yao, Wenlin Foroosh, Hassan Yu, Dong Liu, Fei |
| contents | Reasoning is most powerful when an LLM accurately aggregates relevant information. We examine the critical role of information aggregation in reasoning by requiring the LLM to analyze sports narratives. To succeed at this task, an LLM must infer points from actions, identify related entities, attribute points accurately to players and teams, and compile key statistics to draw conclusions. We conduct comprehensive experiments with real NBA basketball data and present SportsGen, a new method to synthesize game narratives. By synthesizing data, we can rigorously evaluate LLMs' reasoning capabilities under complex scenarios with varying narrative lengths and density of information. Our findings show that most models, including GPT-4o, often fail to accurately aggregate basketball scores due to frequent scoring patterns. Open-source models like Llama-3 further suffer from significant score hallucinations. Finally, the effectiveness of reasoning is influenced by narrative complexity, information density, and domain-specific terms, highlighting the challenges in analytical reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12084 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives Hu, Yebowen Song, Kaiqiang Cho, Sangwoo Wang, Xiaoyang Yao, Wenlin Foroosh, Hassan Yu, Dong Liu, Fei Computation and Language Artificial Intelligence Reasoning is most powerful when an LLM accurately aggregates relevant information. We examine the critical role of information aggregation in reasoning by requiring the LLM to analyze sports narratives. To succeed at this task, an LLM must infer points from actions, identify related entities, attribute points accurately to players and teams, and compile key statistics to draw conclusions. We conduct comprehensive experiments with real NBA basketball data and present SportsGen, a new method to synthesize game narratives. By synthesizing data, we can rigorously evaluate LLMs' reasoning capabilities under complex scenarios with varying narrative lengths and density of information. Our findings show that most models, including GPT-4o, often fail to accurately aggregate basketball scores due to frequent scoring patterns. Open-source models like Llama-3 further suffer from significant score hallucinations. Finally, the effectiveness of reasoning is influenced by narrative complexity, information density, and domain-specific terms, highlighting the challenges in analytical reasoning tasks. |
| title | When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.12084 |