LLM-Symbolic Integration for Robust Temporal Tabular Reasoning

Atharv Kulkarni, Kushagra Dixit, Vivek Srikumar, Dan Roth and Vivek Gupta

Findings of the Association for Computational Linguistics: ACL 2025, 2025.

Abstract

Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data---a task where traditional prompting methods often fall short. These methods face challenges such as memorization, sensitivity to table size, and reduced performance on complex queries. To overcome these limitations, we introduce TEMPTABQA-C, a synthetic dataset designed for systematic and controlled evaluations, alongside a symbolic intermediate representation that transforms tables into database schemas. This structured approach allows LLMs to generate and execute SQL queries, enhancing generalization and mitigating biases. By incorporating adaptive fewshot prompting with contextually tailored examples, our method achieves superior robustness, scalability, and performance. Experimental results consistently highlight improvements across key challenges, setting a new benchmark for robust temporal reasoning with LLMs. Code and TEMPTABQA-C dataset: https:// coral-lab-asu.github.io/llm_symbolic.

Links

Bib Entry 

@inproceedings{kulkarni2025llm-symbolic,
  author = {Kulkarni, Atharv and Dixit, Kushagra and Srikumar, Vivek and Roth, Dan and Gupta, Vivek},
  title = {{{LLM-Symbolic Integration}} for {{Robust Temporal Tabular Reasoning}}},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  year = {2025}
}