Cloud Hosting

How SURGE substantially improves knowledge relevance through targeted augmentation while retaining language fluency

Generative pre-trained models have shown impressive fluency and coherence when used for dialogue agents. However, a key limitation they suffer from is the lack of grounding in external knowledge. Left to their pre-trained parameters alone, these models often generate plausible-sounding but factually incorrect responses, also known as hallucinations.

Prior approaches to mitigate this have involved augmenting the dialogue context with entire knowledge graphs associated with entities mentioned in the chat. However, this indiscriminate conditioning on large knowledge graphs brings its own problems:

Limitations of Naive Knowledge Graph Augmentation:

To overcome this, Kang et al. 2023 propose the SUbgraph Retrieval-augmented GEneration (SURGE) framework, with three key innovations:

This allows providing precisely the requisite factual context to the dialogue without dilution from irrelevant facts or model limitations. Experiments show SURGE reduces hallucination and improves grounding.

Follow this link:

Optimizing Retrieval-Augmented Generation (RAG) by Selective Knowledge Graph Conditioning - Towards Data Science