Temporal Knowledge Question Answering via Abstract Reasoning Induction

TL;DR

This paper introduces the Abstract Reasoning Induction framework to improve temporal knowledge reasoning in Large Language Models by enabling proactive, self-directed learning and separating knowledge phases, resulting in significant performance gains.

Contribution

The paper presents a novel ARI framework that enhances LLMs' temporal reasoning by dividing reasoning into knowledge-agnostic and knowledge-based phases, incorporating constructivist principles for active learning.

Findings

29.7% relative improvement on one dataset

9.27% relative improvement on another dataset

Effective separation of reasoning phases enhances accuracy

Abstract

In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of inaccurate or misleading responses. This issue mainly arises from their limited ability to handle evolving factual knowledge and complex temporal logic. To overcome these limitations, we propose Abstract Reasoning Induction (ARI) framework, which divides temporal reasoning into two distinct phases: Knowledge-agnostic and Knowledge-based. This framework offers factual knowledge support to LLMs while minimizing the incorporation of extraneous noisy data. Concurrently, informed by the principles of constructivism, ARI provides LLMs the capability to engage in proactive, self-directed learning from both correct and incorrect historical reasoning samples. By teaching LLMs to actively construct knowledge and methods, it can significantly boosting their temporal reasoning abilities. Our approach achieves remarkable improvements, with relative gains of 29.7% and 9.27% on two temporal QA datasets, underscoring its efficacy in advancing temporal reasoning in LLMs. The code can be found at https://github.com/czy1999/ARI-QA