An LLM Feature-based Framework for Dialogue Constructiveness Assessment

TL;DR

This paper introduces a hybrid framework combining interpretable linguistic features and large language models to assess dialogue constructiveness, achieving robust and accurate predictions while maintaining interpretability.

Contribution

It proposes a novel LLM feature-based framework that leverages linguistic features extracted via prompting and heuristics, improving over existing models in dialogue constructiveness assessment.

Findings

LLM feature-based models outperform or match neural models.

The framework learns more robust and interpretable prediction rules.

Models generalize well across multiple datasets.

Abstract

Research on dialogue constructiveness assessment focuses on (i) analysing conversational factors that influence individuals to take specific actions, win debates, change their perspectives or broaden their open-mindedness and (ii) predicting constructiveness outcomes following dialogues for such use cases. These objectives can be achieved by training either interpretable feature-based models (which often involve costly human annotations) or neural models such as pre-trained language models (which have empirically shown higher task accuracy but lack interpretability). In this paper we propose an LLM feature-based framework for dialogue constructiveness assessment that combines the strengths of feature-based and neural approaches, while mitigating their downsides. The framework first defines a set of dataset-independent and interpretable linguistic features, which can be extracted by both prompting an LLM and simple heuristics. Such features are then used to train LLM feature-based models. We apply this framework to three datasets of dialogue constructiveness and find that our LLM feature-based models outperform or performs at least as well as standard feature-based models and neural models. We also find that the LLM feature-based model learns more robust prediction rules instead of relying on superficial shortcuts, which often trouble neural models.