VI seminar #43:
A doctoral researcher Nicholas Walker at Norsk Regnesentral presented his work entitled "Graph-Based Reasoning for Dialogue Models" (31. Aug. 2023).
Abstract:
Recent advances in dialogue systems have attracted increasing attention both inside of academic research and in the general public. Language models such as ChatGPT have demonstrated impressive capabilities, but many questions remain about their ability to reason over information and their tendency to “hallucinate” facts. In this talk, I will discuss outstanding issues with logical reasoning and hallucination in large language models and look at a graph-based approach to representing information for use with large language models. In this approach, entities in dialogue such as people, places, or sentences in the conversation are represented as nodes in a graph, with edges corresponding to semantic relations between them. Graph representation in this fashion enables the use of logical rules which can be used to generate text input derived from the graph, which is then made available to a language model. This approach enables explicit representation of logical reasoning about the world, and experiments have shown promise for improving model output and reducing model hallucinations.