In search scenarios, user experience can be hindered by erroneous queries due to typos, voice errors, or knowledge gaps. Therefore, query correction is crucial for search engines. Current correction models, usually small models trained on specific data, often struggle with queries beyond their training scope or those requiring contextual understanding. While the advent of Large Language Models (LLMs) offers a potential solution, they are still limited by their pre-training data and inference cost, particularly for complex queries, making them not always effective for query correction. To tackle these, we propose Trigger$^3$, a large-small model collaboration framework that integrates the traditional correction model and LLM for query correction, capable of adaptively choosing the appropriate correction method based on the query and the correction results from the traditional correction model and LLM. Trigger$^3$ first employs a correction trigger to filter out correct queries. Incorrect queries are then corrected by the traditional correction model. If this fails, an LLM trigger is activated to call the LLM for correction. Finally, for queries that no model can correct, a fallback trigger decides to return the original query. Extensive experiments demonstrate Trigger$^3$ outperforms correction baselines while maintaining efficiency.

翻译：在搜索场景中，因拼写错误、语音识别错误或知识差距导致的错误查询会损害用户体验。因此，查询纠错对搜索引擎至关重要。当前的纠错模型通常是基于特定数据训练的小型模型，往往难以处理超出其训练范围的查询或需要上下文理解的查询。虽然大型语言模型的出现提供了一种潜在的解决方案，但它们仍受限于预训练数据和推理成本，尤其对于复杂查询，使其在查询纠错中并非总是有效。为解决这些问题，我们提出了Trigger$^3$，一个大小模型协作框架，它整合了传统纠错模型与大型语言模型进行查询纠错，能够根据查询以及传统纠错模型和大型语言模型的纠错结果，自适应地选择合适的纠错方法。Trigger$^3$首先使用一个纠错触发器过滤掉正确的查询。错误的查询随后由传统纠错模型进行纠正。若此步骤失败，则激活一个大型语言模型触发器以调用大型语言模型进行纠错。最后，对于任何模型都无法纠正的查询，一个回退触发器决定返回原始查询。大量实验表明，Trigger$^3$在保持效率的同时，其性能优于现有的纠错基线方法。