@inproceedings{gasan-pais-2025-sag,
title = "{SAG}: Enhancing Domain-Specific Information Retrieval with Semantic-Augmented Graphs",
author = "Gasan, Carol-Luca and
Pais, Vasile",
editor = "Frermann, Lea and
Stevenson, Mark",
booktitle = "Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*{SEM} 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.starsem-1.29/",
doi = "10.18653/v1/2025.starsem-1.29",
pages = "362--371",
ISBN = "979-8-89176-340-1",
abstract = "Retrieval-Augmented Generation (RAG) systems rely on high-quality embeddings to retrieve relevant context for large language models. This paper introduces the Semantic-Augmented Graph (SAG), a new architecture that improves domain-specific embeddings by capturing hierarchical semantic relationships between text segments. Inspired by human information processing, SAG organizes content from general to specific concepts using a graph-based structure. By combining static embeddings with dynamic semantic graphs, it generates context-aware representations that reflect both lexical and conceptual links. Experiments on text similarity and domain-specific question answering show that SAG consistently outperforms standard embedding methods within RAG pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gasan-pais-2025-sag">
<titleInfo>
<title>SAG: Enhancing Domain-Specific Information Retrieval with Semantic-Augmented Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carol-Luca</namePart>
<namePart type="family">Gasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasile</namePart>
<namePart type="family">Pais</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 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Stevenson</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">979-8-89176-340-1</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) systems rely on high-quality embeddings to retrieve relevant context for large language models. This paper introduces the Semantic-Augmented Graph (SAG), a new architecture that improves domain-specific embeddings by capturing hierarchical semantic relationships between text segments. Inspired by human information processing, SAG organizes content from general to specific concepts using a graph-based structure. By combining static embeddings with dynamic semantic graphs, it generates context-aware representations that reflect both lexical and conceptual links. Experiments on text similarity and domain-specific question answering show that SAG consistently outperforms standard embedding methods within RAG pipelines.</abstract>
<identifier type="citekey">gasan-pais-2025-sag</identifier>
<identifier type="doi">10.18653/v1/2025.starsem-1.29</identifier>
<location>
<url>https://aclanthology.org/2025.starsem-1.29/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>362</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAG: Enhancing Domain-Specific Information Retrieval with Semantic-Augmented Graphs
%A Gasan, Carol-Luca
%A Pais, Vasile
%Y Frermann, Lea
%Y Stevenson, Mark
%S Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-340-1
%F gasan-pais-2025-sag
%X Retrieval-Augmented Generation (RAG) systems rely on high-quality embeddings to retrieve relevant context for large language models. This paper introduces the Semantic-Augmented Graph (SAG), a new architecture that improves domain-specific embeddings by capturing hierarchical semantic relationships between text segments. Inspired by human information processing, SAG organizes content from general to specific concepts using a graph-based structure. By combining static embeddings with dynamic semantic graphs, it generates context-aware representations that reflect both lexical and conceptual links. Experiments on text similarity and domain-specific question answering show that SAG consistently outperforms standard embedding methods within RAG pipelines.
%R 10.18653/v1/2025.starsem-1.29
%U https://aclanthology.org/2025.starsem-1.29/
%U https://doi.org/10.18653/v1/2025.starsem-1.29
%P 362-371
Markdown (Informal)
[SAG: Enhancing Domain-Specific Information Retrieval with Semantic-Augmented Graphs](https://aclanthology.org/2025.starsem-1.29/) (Gasan & Pais, *SEM 2025)
ACL