Integrating Large Language Model and Mental Model of Others: Studies on Dialogue Communication Based on Implicature
Open Access
- 24 November 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 260-269
Abstract
Despite the significant development of Large Language Models (LLMs), they struggle with “dialogue communication based on implicature,” which humans handle easily. In this study, we aim to improve the performance of LLMs in this type of dialogue tasks by integrating LLMs with a cognitive model of dialogue. The cognitive model of dialogue comprises beliefs, desires, and intentions, which is defined as the Mental Model of Others (MMO) for predicting or estimating other’s mental states and behaviors. We propose two integration methods: the LLM Embedded in Cognitive Model (LEC) and the Cognitive Model Embedded in LLM (CEL). We examined the performances of our proposed method using the dialogue task, showing that the LEC can respond appropriately in the dialogues with implicatures, which cannot be achieved by conventional LLMs.Keywords
This publication has 7 references indexed in Scilit:
- Large language models can infer psychological dispositions of social media usersPNAS Nexus, 2024
- Comparing Children and Large Language Models in Word Sense Disambiguation: Insights and ChallengesPsyArXiv, 2023
- A fine-grained comparison of pragmatic language understanding in humans and language models2023
- Classification and Prospects for HAI Research Based on a Tentative Framework2020
- Probabilistic modeling of mental models of others2015
- Computational Modeling of Human-Robot Interaction Based on Active Intention Estimation2008
- Computer science as empirical inquiryCommunications of the ACM, 1976