UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization

TL;DR

UnSeenTimeQA is a new benchmark for testing large language models' ability to perform time-sensitive reasoning without relying on pre-existing knowledge, using synthetic, contamination-free data.

Contribution

The paper introduces UnSeenTimeQA, a novel, contamination-free TSQA benchmark with synthetic data and a flexible generation framework for evaluating LLMs' temporal reasoning.

Findings

LLMs perform well on simple questions but struggle with complex event dependencies.

Performance is lower compared to real-world fact-based TSQA.

Error analysis highlights difficulties in reasoning over long-range and parallel events.

Abstract

This paper introduces UnSeenTimeQA, a novel data contamination-free time-sensitive question-answering (TSQA) benchmark. It differs from existing TSQA benchmarks by avoiding web-searchable queries grounded in the real world. We present a series of time-sensitive event scenarios based on synthetically generated facts. It requires large language models (LLMs) to engage in genuine temporal reasoning without depending on the factual knowledge acquired during the pre-training phase. Our data generation framework enables on-demand generation of new samples, mitigating the risk of data leakage. We designed three types of time-sensitive questions to test LLMs' temporal reasoning abilities over sequential and parallel event occurrences. Our evaluation of five LLMs on synthetic fact-based TSQA reveals mixed results: while they perform well on simpler subsets, their overall performance remains inferior as compared to real world fact-based TSQA. Error analysis indicates that LLMs face difficulties in reasoning over long-range event dependencies and parallel events.