Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection
Libo Qin, Qiguang Chen, Jingxuan Zhou, Jin Wang, Hao Fei, Wanxiang Che, Min Li
Abstract
Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-shot multi-intent detection. While significant advancements have been witnessed, the existing prompting approaches still face two major issues: lacking explicit reasoning and lacking interpretability. Therefore, in this paper, we introduce a Divide-Solve-Combine Prompting (DSCP) to address the above issues. Specifically, DSCP explicitly decomposes multi-intent detection into three components including (1) single-intent division prompting is utilized to decompose an input query into distinct sub-sentences, each containing a single intent; (2) intent-by-intent solution prompting is applied to solve each sub-sentence recurrently; and (3) multi-intent combination prompting is employed for combining each sub-sentence result to obtain the final multi-intent result. By decomposition, DSCP allows the model to track the explicit reasoning process and improve the interpretability. In addition, we propose an interactive divide-solve-combine prompting (Inter-DSCP) to naturally capture the interaction capabilities of large language models. Experimental results on two standard multi-intent benchmarks (i.e., MixATIS and MixSNIPS) reveal that both DSCP and Inter-DSCP obtain substantial improvements over baselines, achieving superior performance and higher interpretability.
BibTeX
@article{Qin_Chen_Zhou_Wang_Fei_Che_Li_2025, title={Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34688}, DOI={10.1609/aaai.v39i23.34688}, abstractNote={Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-shot multi-intent detection. While significant advancements have been witnessed, the existing prompting approaches still face two major issues: lacking explicit reasoning and lacking interpretability. Therefore, in this paper, we introduce a Divide-Solve-Combine Prompting (DSCP) to address the above issues.
Specifically, DSCP explicitly decomposes multi-intent detection into three components including (1) single-intent division prompting is utilized to decompose an input query into distinct sub-sentences, each containing a single intent; (2) intent-by-intent solution prompting is applied to solve each sub-sentence recurrently; and (3) multi-intent combination prompting is employed for combining each sub-sentence result to obtain the final multi-intent result. By decomposition, DSCP allows the model to track the explicit reasoning process and improve the interpretability. In addition, we propose an interactive divide-solve-combine prompting (Inter-DSCP) to naturally capture the interaction capabilities of large language models. Experimental results on two standard multi-intent benchmarks (i.e., MixATIS and MixSNIPS) reveal that both DSCP and Inter-DSCP obtain substantial improvements over baselines, achieving superior performance and higher interpretability.}, number={23}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Qin, Libo and Chen, Qiguang and Zhou, Jingxuan and Wang, Jin and Fei, Hao and Che, Wanxiang and Li, Min}, year={2025}, month={Apr.}, pages={25038-25046} }