@inproceedings{kim-etal-2025-tides,
title = "{TIDES}: Technical Information Discovery and Extraction System",
author = "Kim, Jihee and
Park, Subeen and
Lee, Hakyung and
Lim, YongTaek and
Suh, Hyo-won and
Song, Kyungwoo",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1103/",
doi = "10.18653/v1/2025.emnlp-main.1103",
pages = "21756--21772",
ISBN = "979-8-89176-332-6",
abstract = "Addressing the challenges in QA for specific technical domains requires identifying relevant portions of extensive documents and generating answers based on this focused content. Traditional pre-trained LLMs often struggle with domain-specific terminology, while fine-tuned LLMs demand substantial computational resources. To overcome these limitations, we propose TIDES, Technical Information Distillation and Extraction System. TIDES is a training-free approach that combines traditional TF-IDF techniques with prompt-based LLMs in a hybrid process, effectively addressing complex technical questions. It uses TF-IDF to identify and prioritize domain-specific words that are rare in other documents and LLMs to refine the candidate pool by focusing on the most relevant segments in documents through multiple stages. Our approach improves the precision and efficiency of QA systems in technical contexts without LLM retraining."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-tides">
<titleInfo>
<title>TIDES: Technical Information Discovery and Extraction System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihee</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subeen</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hakyung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">YongTaek</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyo-won</namePart>
<namePart type="family">Suh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungwoo</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Addressing the challenges in QA for specific technical domains requires identifying relevant portions of extensive documents and generating answers based on this focused content. Traditional pre-trained LLMs often struggle with domain-specific terminology, while fine-tuned LLMs demand substantial computational resources. To overcome these limitations, we propose TIDES, Technical Information Distillation and Extraction System. TIDES is a training-free approach that combines traditional TF-IDF techniques with prompt-based LLMs in a hybrid process, effectively addressing complex technical questions. It uses TF-IDF to identify and prioritize domain-specific words that are rare in other documents and LLMs to refine the candidate pool by focusing on the most relevant segments in documents through multiple stages. Our approach improves the precision and efficiency of QA systems in technical contexts without LLM retraining.</abstract>
<identifier type="citekey">kim-etal-2025-tides</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1103</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1103/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>21756</start>
<end>21772</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TIDES: Technical Information Discovery and Extraction System
%A Kim, Jihee
%A Park, Subeen
%A Lee, Hakyung
%A Lim, YongTaek
%A Suh, Hyo-won
%A Song, Kyungwoo
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F kim-etal-2025-tides
%X Addressing the challenges in QA for specific technical domains requires identifying relevant portions of extensive documents and generating answers based on this focused content. Traditional pre-trained LLMs often struggle with domain-specific terminology, while fine-tuned LLMs demand substantial computational resources. To overcome these limitations, we propose TIDES, Technical Information Distillation and Extraction System. TIDES is a training-free approach that combines traditional TF-IDF techniques with prompt-based LLMs in a hybrid process, effectively addressing complex technical questions. It uses TF-IDF to identify and prioritize domain-specific words that are rare in other documents and LLMs to refine the candidate pool by focusing on the most relevant segments in documents through multiple stages. Our approach improves the precision and efficiency of QA systems in technical contexts without LLM retraining.
%R 10.18653/v1/2025.emnlp-main.1103
%U https://aclanthology.org/2025.emnlp-main.1103/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1103
%P 21756-21772
Markdown (Informal)
[TIDES: Technical Information Discovery and Extraction System](https://aclanthology.org/2025.emnlp-main.1103/) (Kim et al., EMNLP 2025)
ACL
- Jihee Kim, Subeen Park, Hakyung Lee, YongTaek Lim, Hyo-won Suh, and Kyungwoo Song. 2025. TIDES: Technical Information Discovery and Extraction System. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21756–21772, Suzhou, China. Association for Computational Linguistics.