LLM-Symbolic Integration for Robust Temporal Tabular Reasoning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kulkarni, Atharv, Dixit, Kushagra, Srikumar, Vivek, Roth, Dan, Gupta, Vivek
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909640961294336
author Kulkarni, Atharv
Dixit, Kushagra
Srikumar, Vivek
Roth, Dan
Gupta, Vivek
author_facet Kulkarni, Atharv
Dixit, Kushagra
Srikumar, Vivek
Roth, Dan
Gupta, Vivek
contents Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data, which is 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 few-shot 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05746
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
Kulkarni, Atharv
Dixit, Kushagra
Srikumar, Vivek
Roth, Dan
Gupta, Vivek
Computation and Language
Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data, which is 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 few-shot 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.
title LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
topic Computation and Language
url https://arxiv.org/abs/2506.05746