Trigger$^3$: Refining Query Correction via Adaptive Model Selector

TL;DR

Trigger$^3$ introduces an adaptive framework combining traditional models and large language models for query correction, improving accuracy and efficiency in handling diverse erroneous search queries.

Contribution

The paper presents a novel collaborative framework that adaptively selects correction methods, enhancing query correction performance over existing models.

Findings

Trigger$^3$ outperforms baseline correction methods in accuracy.

The framework effectively filters correct queries, reducing unnecessary corrections.

Trigger$^3$ maintains efficiency while improving correction quality.

Abstract

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.