LLM-Symbolic Integration for Robust Temporal Tabular Reasoning

ACL ARR 2024 December Submission1781 Authors

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 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.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: logical reasoning, benchmarking, automatic creation and evaluation of language resources, NLP datasets, logical reasoning, reasoning, table QA, few-shot learning, robustness, document-level extraction

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources, Data analysis

Languages Studied: English

Submission Number: 1781