Year: 2026
Type: conference-paper
Abstract: Large language model (LLM) approaches to tabular summarization rely on extensive prompt engineering, decomposition pipelines, or entitylevel intermediate representations to achieve strong performance.While effective, these strategies are computationally expensive and offer limited insight into how well models maintain state over long, evolving narratives.We introduce SPORTABSET, a diagnostic benchmark for long-context tabular summarization across two complementary sports domains that require tracking multiple entities and aggregating statistics under domain-specific rules.Using SporTabSet, we systematically evaluate decomposition-based strategies across several long context LLMs.Results show that although decomposition substantially improves accuracy and numerical fidelity, gains stem mainly from dissecting multi-entity interference rather than improved local arithmetic.Robustness experiments further reveal high sensitivity to surfacelevel cues with structured failures, including hallucination, omission, and role confusion.Together, these findings identify consistent multientity memory as a key bottleneck in longcontext table generation, motivating diagnostic evaluation as a prerequisite for scalable, efficient, and reliable tabular summarization models.
Authors: Ritam Upadhyay, Naman Ahuja, Rishabh Baral, Aparna Garimella, Vivek Gupta
Institution: Arizona State University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Arizona State University
OpenAlex ID: W4416055197