No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913979627995136 |
|---|---|
| author | Rajgaria, Abhishek Dixit, Kushagra Vyas, Mayank Kalalbandi, Harshavardhan Roth, Dan Gupta, Vivek |
| author_facet | Rajgaria, Abhishek Dixit, Kushagra Vyas, Mayank Kalalbandi, Harshavardhan Roth, Dan Gupta, Vivek |
| contents | Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs), requiring effective reasoning to extract relevant insights. Despite existence of multiple prompting methods, their impact on table reasoning remains largely unexplored. Furthermore, model performance varies drastically across different table and context structures, making it difficult to determine an optimal approach. This work investigates multiple prompting technique on diverse table types to determine that performance depends on factors such as entity type, table structure, requirement of additional context and question complexity, with "NO" single method consistently outperforming others. To address this, we introduce SEAR, an adaptive prompting framework inspired by human reasoning that dynamically adjusts to context and integrates structured reasoning. Our results demonstrate that SEAR achieves superior performance across all table types compared to baseline prompting techniques. Additionally, we explore the impact of table structure refactoring, finding that a unified representation enhances model reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11246 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning Rajgaria, Abhishek Dixit, Kushagra Vyas, Mayank Kalalbandi, Harshavardhan Roth, Dan Gupta, Vivek Computation and Language Artificial Intelligence Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs), requiring effective reasoning to extract relevant insights. Despite existence of multiple prompting methods, their impact on table reasoning remains largely unexplored. Furthermore, model performance varies drastically across different table and context structures, making it difficult to determine an optimal approach. This work investigates multiple prompting technique on diverse table types to determine that performance depends on factors such as entity type, table structure, requirement of additional context and question complexity, with "NO" single method consistently outperforming others. To address this, we introduce SEAR, an adaptive prompting framework inspired by human reasoning that dynamically adjusts to context and integrates structured reasoning. Our results demonstrate that SEAR achieves superior performance across all table types compared to baseline prompting techniques. Additionally, we explore the impact of table structure refactoring, finding that a unified representation enhances model reasoning. |
| title | No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.11246 |