DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mehta, Rahul, R V, Kavin, Pal, Indrajit, Abhishek, Tushar, Goyal, Pawan, Gupta, Manish
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913047625334784
author Mehta, Rahul
R V, Kavin
Pal, Indrajit
Abhishek, Tushar
Goyal, Pawan
Gupta, Manish
author_facet Mehta, Rahul
R V, Kavin
Pal, Indrajit
Abhishek, Tushar
Goyal, Pawan
Gupta, Manish
contents Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance search productivity within long documents by helping users craft faster, more precise queries, even for complex or hard-to-spell terms. While global historical queries are available to both WebQAC and DocQAC, DocQAC uniquely accesses document-specific context, including the current document's content and its specific history of user query interactions. To address this setting, we propose a novel adaptive trie-guided decoding framework that uses user query prefixes to softly steer language models toward high-quality completions. Our approach introduces an adaptive penalty mechanism with tunable hyperparameters, enabling a principled trade-off between model confidence and trie-based guidance. To efficiently incorporate document context, we explore retrieval-augmented generation (RAG) and lightweight contextual document signals such as titles, keyphrases, and summaries. When applied to encoder-decoder models like T5 and BART, our trie-guided framework outperforms strong baselines and even surpasses much larger instruction-tuned models such as LLaMA-3 and Phi-3 on seen queries across both seen and unseen documents. This demonstrates its practicality for real-world DocQAC deployments, where efficiency and scalability are critical. We evaluate our method on a newly introduced DocQAC benchmark derived from ORCAS, enriched with query-document pairs. We make both the DocQAC dataset (https://bit.ly/3IGEkbH) and code (https://github.com/rahcode7/DocQAC) publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18257
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
Mehta, Rahul
R V, Kavin
Pal, Indrajit
Abhishek, Tushar
Goyal, Pawan
Gupta, Manish
Information Retrieval
Artificial Intelligence
Computation and Language
Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance search productivity within long documents by helping users craft faster, more precise queries, even for complex or hard-to-spell terms. While global historical queries are available to both WebQAC and DocQAC, DocQAC uniquely accesses document-specific context, including the current document's content and its specific history of user query interactions. To address this setting, we propose a novel adaptive trie-guided decoding framework that uses user query prefixes to softly steer language models toward high-quality completions. Our approach introduces an adaptive penalty mechanism with tunable hyperparameters, enabling a principled trade-off between model confidence and trie-based guidance. To efficiently incorporate document context, we explore retrieval-augmented generation (RAG) and lightweight contextual document signals such as titles, keyphrases, and summaries. When applied to encoder-decoder models like T5 and BART, our trie-guided framework outperforms strong baselines and even surpasses much larger instruction-tuned models such as LLaMA-3 and Phi-3 on seen queries across both seen and unseen documents. This demonstrates its practicality for real-world DocQAC deployments, where efficiency and scalability are critical. We evaluate our method on a newly introduced DocQAC benchmark derived from ORCAS, enriched with query-document pairs. We make both the DocQAC dataset (https://bit.ly/3IGEkbH) and code (https://github.com/rahcode7/DocQAC) publicly available.
title DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.18257