Keywords: Algebraic representation, Fock space, LLM, PPI
Abstract: Recent results show that modern Large Language Models (LLM) are indeed capable of understanding and answering questions about structured data such as graphs.
%Works like GraphToken and GraphLLM have demonstrated,
Existing proposals often use some
description of the graph to
create an ``augmented'' prompt fed to the LLM.
For a chosen class of graphs, if a well-tailored graph encoder is
deployed to play together with a pre-trained LLM, the model can answer graph-related questions well.
%In this work, we expand greatly on these approaches.
Existing solutions to graph-based prompts range
from graph serialization to graph transformers.
In this work, we show that the use of a parameter-free graph encoder based on Fock space representations, a concept borrowed from mathematical physics, is remarkably versatile in this problem setting.
The simple construction, inherited directly from
the theory with a few small adjustments, can provide rich and informative graph encodings, for a wide range of different graphs. We investigate the use of this idea for prefix-tuned prompts leveraging the capabilities of a pre-trained, frozen LLM. The modifications lead to a model that can answer graph-related questions -- from simple graphs to proteins to hypergraphs -- effectively and with minimal, if any, adjustments to the architecture. Our work significantly simplifies existing solutions and generalizes well to multiple different graph-based structures effortlessly.
Submission Number: 42
Loading