Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought
This addresses the challenge of handling complex multi-choice queries in dialogue systems, offering a novel approach for improved commonsense inference, though it appears incremental as it builds on existing graph-of-thought methods.
The paper tackles the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task by proposing a Reverse Exclusion Graph-of-Thought (ReX-GoT) framework that mimics human reasoning to exclude irrelevant options, achieving a 17.67% F1 score improvement over baselines in zero-shot settings and a 39.44% increase with GPT3.5.
With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions. Although prevailing methodologies exhibit effectiveness in addressing single-choice questions, they encounter difficulties in handling multi-choice queries due to the heightened intricacy and informational density. In this paper, inspired by the human cognitive process of progressively excluding options, we propose a three-step Reverse Exclusion Graph-of-Thought (ReX-GoT) framework, including Option Exclusion, Error Analysis, and Combine Information. Specifically, our ReX-GoT mimics human reasoning by gradually excluding irrelevant options and learning the reasons for option errors to choose the optimal path of the GoT and ultimately infer the correct answer. By progressively integrating intricate clues, our method effectively reduces the difficulty of multi-choice reasoning and provides a novel solution for DC-MCQ. Extensive experiments on the CICERO and CICERO$_{v2}$ datasets validate the significant improvement of our approach on DC-MCQ task. On zero-shot setting, our model outperform the best baseline by 17.67% in terms of F1 score for the multi-choice task. Most strikingly, our GPT3.5-based ReX-GoT framework achieves a remarkable 39.44% increase in F1 score.