@inproceedings{mahalingam-etal-2025-sketch,
title = "{SKETCH}: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval",
author = "Mahalingam, Aakash and
Gande, Vinesh Kumar and
Chadha, Aman and
Jain, Vinija and
Chaudhary, Divya",
editor = "Gesese, Genet Asefa and
Sack, Harald and
Paulheim, Heiko and
Merono-Penuela, Albert and
Chen, Lihu",
booktitle = "Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.genaik-1.4/",
pages = "27--42",
abstract = "This paper discusses about the SKETCH approach which enhances text retrieval and context relevancy on large corpuses compared to the traditional baseline methods. The abstract attached below discusses this further. Abstract: Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine{---}SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer relevancy, faithfulness, context precision and context recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH`s capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahalingam-etal-2025-sketch">
<titleInfo>
<title>SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aakash</namePart>
<namePart type="family">Mahalingam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinesh</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Gande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Chadha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinija</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divya</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Genet</namePart>
<namePart type="given">Asefa</namePart>
<namePart type="family">Gesese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Sack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heiko</namePart>
<namePart type="family">Paulheim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Merono-Penuela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses about the SKETCH approach which enhances text retrieval and context relevancy on large corpuses compared to the traditional baseline methods. The abstract attached below discusses this further. Abstract: Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine—SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer relevancy, faithfulness, context precision and context recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH‘s capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems.</abstract>
<identifier type="citekey">mahalingam-etal-2025-sketch</identifier>
<location>
<url>https://aclanthology.org/2025.genaik-1.4/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>27</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval
%A Mahalingam, Aakash
%A Gande, Vinesh Kumar
%A Chadha, Aman
%A Jain, Vinija
%A Chaudhary, Divya
%Y Gesese, Genet Asefa
%Y Sack, Harald
%Y Paulheim, Heiko
%Y Merono-Penuela, Albert
%Y Chen, Lihu
%S Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F mahalingam-etal-2025-sketch
%X This paper discusses about the SKETCH approach which enhances text retrieval and context relevancy on large corpuses compared to the traditional baseline methods. The abstract attached below discusses this further. Abstract: Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine—SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer relevancy, faithfulness, context precision and context recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH‘s capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems.
%U https://aclanthology.org/2025.genaik-1.4/
%P 27-42
Markdown (Informal)
[SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval](https://aclanthology.org/2025.genaik-1.4/) (Mahalingam et al., GenAIK 2025)
ACL