Time-Continuous Modeling for Temporal Affective Pattern Recognition in LLMs

TL;DR

This paper presents a new dataset and framework enabling large language models to emulate real-world emotional changes over time, enhancing interpretability in dialogue systems using physics-informed neural networks.

Contribution

It introduces a novel dataset and conceptual framework for modeling temporal affective patterns in LLMs with physics-informed neural networks.

Findings

Demonstrates the feasibility of modeling emotional dynamics over time.

Provides a new dataset for temporal affective pattern recognition.

Suggests improved interpretability in dialogue modeling.

Abstract

This paper introduces a dataset and conceptual framework for LLMs to mimic real world emotional dynamics through time and in-context learning leveraging physics-informed neural network, opening a possibility for interpretable dialogue modeling.