@inproceedings{suyasri-etal-2026-empirical,
title = "An Empirical Study of Evidence Retrieval for Retrieval Augmented Generation over the {T}hai Royal Gazette",
author = "Suyasri, Pantai and
Akarajaradwong, Pawitsapak and
Chaksangchaichot, Chompakorn",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preoțiuc-Pietro, Daniel and
Spanakis, Gerasimos and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.19/",
pages = "212--236",
ISBN = "979-8-89176-494-1",
abstract = "Retrieval-augmented generation depends on both the retrieval method and the units over which retrieval operates. Yet retrieval-unit choices remain underexplored for Thai legal documents, where language and document structure challenge common chunking assumptions. We introduce a 2,000-question Thai Royal Gazette dataset with single-hop and multi-hop tasks. The dataset annotates gold evidence as document character spans, which permits unit-independent evaluation. We compare 19 configurations across chunk sizes, boundary strategies, contextual chunks, atomic facts, whole documents, and retrieval methods. We evaluate them with span recall and precision, an Evidence-Fit judge, and pairwise judgments of answers generated from retrieved evidence. Contextual 200-word chunks with hybrid retrieval provide the strongest practical balance of evidence coverage, answer quality, and query cost. Across configurations, downstream scores correlate strongly with span recall, while span precision shows little association. These results favor retrieval designs that first recover complete evidence, then control cost and localization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suyasri-etal-2026-empirical">
<titleInfo>
<title>An Empirical Study of Evidence Retrieval for Retrieval Augmented Generation over the Thai Royal Gazette</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pantai</namePart>
<namePart type="family">Suyasri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawitsapak</namePart>
<namePart type="family">Akarajaradwong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chompakorn</namePart>
<namePart type="family">Chaksangchaichot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goanță</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>Retrieval-augmented generation depends on both the retrieval method and the units over which retrieval operates. Yet retrieval-unit choices remain underexplored for Thai legal documents, where language and document structure challenge common chunking assumptions. We introduce a 2,000-question Thai Royal Gazette dataset with single-hop and multi-hop tasks. The dataset annotates gold evidence as document character spans, which permits unit-independent evaluation. We compare 19 configurations across chunk sizes, boundary strategies, contextual chunks, atomic facts, whole documents, and retrieval methods. We evaluate them with span recall and precision, an Evidence-Fit judge, and pairwise judgments of answers generated from retrieved evidence. Contextual 200-word chunks with hybrid retrieval provide the strongest practical balance of evidence coverage, answer quality, and query cost. Across configurations, downstream scores correlate strongly with span recall, while span precision shows little association. These results favor retrieval designs that first recover complete evidence, then control cost and localization.</abstract>
<identifier type="citekey">suyasri-etal-2026-empirical</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>212</start>
<end>236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study of Evidence Retrieval for Retrieval Augmented Generation over the Thai Royal Gazette
%A Suyasri, Pantai
%A Akarajaradwong, Pawitsapak
%A Chaksangchaichot, Chompakorn
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F suyasri-etal-2026-empirical
%X Retrieval-augmented generation depends on both the retrieval method and the units over which retrieval operates. Yet retrieval-unit choices remain underexplored for Thai legal documents, where language and document structure challenge common chunking assumptions. We introduce a 2,000-question Thai Royal Gazette dataset with single-hop and multi-hop tasks. The dataset annotates gold evidence as document character spans, which permits unit-independent evaluation. We compare 19 configurations across chunk sizes, boundary strategies, contextual chunks, atomic facts, whole documents, and retrieval methods. We evaluate them with span recall and precision, an Evidence-Fit judge, and pairwise judgments of answers generated from retrieved evidence. Contextual 200-word chunks with hybrid retrieval provide the strongest practical balance of evidence coverage, answer quality, and query cost. Across configurations, downstream scores correlate strongly with span recall, while span precision shows little association. These results favor retrieval designs that first recover complete evidence, then control cost and localization.
%U https://aclanthology.org/2026.nllp-1.19/
%P 212-236
Markdown (Informal)
[An Empirical Study of Evidence Retrieval for Retrieval Augmented Generation over the Thai Royal Gazette](https://aclanthology.org/2026.nllp-1.19/) (Suyasri et al., NLLP 2026)
ACL