Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph Forecasting

TL;DR

This paper introduces sLA-tKGF, a retrieval-augmented, small-scale language model framework for temporal knowledge graph forecasting, reducing hallucinations and improving accuracy by leveraging external knowledge and a tabula rasa approach.

Contribution

It presents a novel retrieval-augmented, small-scale language model framework that effectively forecasts future events in temporal knowledge graphs from scratch.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Reduces hallucinations and biases in predictions.

Demonstrates robustness and scalability in empirical studies.

Abstract

Pre-trained large language models (PLLMs) like OpenAI ChatGPT and Google Gemini face challenges such as inaccurate factual recall, hallucinations, biases, and future data leakage for temporal Knowledge Graph (tKG) forecasting. To address these issues, we introduce sLA-tKGF (small-scale language assistant for tKG forecasting), which utilizes Retrieval-Augmented Generation (RAG) aided, custom-trained small-scale language models through a tabula rasa approach from scratch for effective tKG forecasting. Our framework constructs knowledge-infused prompts with relevant historical data from tKGs, web search results, and PLLMs-generated textual descriptions to understand historical entity relationships prior to the target time. It leverages these external knowledge-infused prompts for deeper understanding and reasoning of context-specific semantic and temporal information to zero-shot prompt small-scale language models for more accurate predictions of future events within tKGs. It reduces hallucinations and mitigates distributional shift challenges through comprehending changing trends over time. As a result, it enables more accurate and contextually grounded forecasts of future events while minimizing computational demands. Rigorous empirical studies demonstrate our framework robustness, scalability, and state-of-the-art (SOTA) performance on benchmark datasets with interpretable and trustworthy tKG forecasting.