No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
Abhishek Rajgaria, Kushagra Dixit, Mayank Vyas, Harshavardhan Kalalbandi, Dan Roth, Vivek Gupta

TL;DR
This paper investigates how different prompting methods affect large language models' reasoning over temporal tables, revealing that no single method is best and proposing an adaptive framework, SEAR, that improves reasoning across diverse table types.
Contribution
The paper introduces SEAR, an adaptive prompting framework that dynamically adjusts to context, significantly enhancing reasoning performance over various temporal table structures.
Findings
Performance varies with table and context structure.
SEAR outperforms baseline prompting methods.
Unified table representation improves reasoning.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLogic, Reasoning, and Knowledge · Semantic Web and Ontologies · Constraint Satisfaction and Optimization
