# Efficient Neural Query Auto Completion

arXiv: https://arxiv.org/abs/2008.02879 · HTML: https://mlsanity.com/paper/2008.02879/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion](https://mlsanity.com/paper/2204.10936/) (2022)
- [Sequential Decision-Making for Inline Text Autocomplete](https://mlsanity.com/paper/2403.15502/) (2024)
- [Unexpected Knowledge: Auditing Wikipedia and Grokipedia Search Recommendations](https://mlsanity.com/paper/2512.17027/) (2025)
- [Search Intenion Network for Personalized Query Auto-Completion in E-Commerce](https://mlsanity.com/paper/2403.02609/) (2024)
- [Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems](https://mlsanity.com/paper/2507.05940/) (2025)
- [Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints](https://mlsanity.com/paper/2210.03251/) (2022)
- [Synthetic Prefixes to Mitigate Bias in Real-Time Neural Query Autocomplete](https://mlsanity.com/paper/2510.01574/) (2025)
- [Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs](https://mlsanity.com/paper/2601.05851/) (2026)
- [Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment](https://mlsanity.com/paper/2602.01023/) (2026)
- [DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion](https://mlsanity.com/paper/2604.18257/) (2026)

## Abstract (arXiv)

Query Auto Completion (QAC), as the starting point of information retrieval tasks, is critical to user experience. Generally it has two steps: generating completed query candidates according to query prefixes, and ranking them based on extracted features. Three major challenges are observed for a query auto completion system: (1) QAC has a strict online latency requirement. For each keystroke, results must be returned within tens of milliseconds, which poses a significant challenge in designing sophisticated language models for it. (2) For unseen queries, generated candidates are of poor quality as contextual information is not fully utilized. (3) Traditional QAC systems heavily rely on handcrafted features such as the query candidate frequency in search logs, lacking sufficient semantic understanding of the candidate. In this paper, we propose an efficient neural QAC system with effective context modeling to overcome these challenges. On the candidate generation side, this system uses as much information as possible in unseen prefixes to generate relevant candidates, increasing the recall by a large margin. On the candidate ranking side, an unnormalized language model is proposed, which effectively captures deep semantics of queries. This approach presents better ranking performance over state-of-the-art neural ranking methods and reduces ~95% latency compared to neural language modeling methods. The empirical results on public datasets show that our model achieves a good balance between accuracy and efficiency. This system is served in LinkedIn job search with significant product impact observed.