@inproceedings{lv-etal-2026-saga,
title = "{SAGA}: Structured Applicability-Guided Alignment for Conversational Legal Retrieval",
author = "Lv, Xinxuan and
Li, Minghan and
Zhou, Guodong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.702/",
pages = "16207--16226",
ISBN = "979-8-89176-459-0",
abstract = "Conversational legal retrieval requires identifying statutes that are better aligned with a user{'}s case context, even when relevant facts are revealed incrementally and incompletely across dialogue turns. Sparse and dense retrievers may return semantically related statutes that are poorly matched to these factual conditions. We propose SAGA, a training-free legal retrieval framework that injects structured applicability-oriented cues into dense retrieval. SAGA constructs a Case Applicability Frame (CAF) from user-side dialogue context to summarize dispute issues, core facts, and missing facts, and uses an offline Article Applicability Frame (AAF) to represent statute-side issue tags, prerequisites, legal effects, and evidence cues. It combines raw semantic and structural applicability streams through late fusion. Experiments on two Chinese statute retrieval benchmarks, LexRAG and STARD, show that SAGA improves over strong sparse, dense, and LLM-enhanced baselines under a unified full-corpus protocol. SAGA yields statistically significant gains on the conversational LexRAG benchmark and more modest gains on STARD over the strongest dense baseline, improving nDCG@10 from 0.3504 to 0.3696 and from 0.5862 to 0.5940, respectively. These results suggest that structured applicability-oriented cues provide useful retrieval signals beyond raw semantic matching, especially in conversational legal retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lv-etal-2026-saga">
<titleInfo>
<title>SAGA: Structured Applicability-Guided Alignment for Conversational Legal Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinxuan</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Zhou</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Conversational legal retrieval requires identifying statutes that are better aligned with a user’s case context, even when relevant facts are revealed incrementally and incompletely across dialogue turns. Sparse and dense retrievers may return semantically related statutes that are poorly matched to these factual conditions. We propose SAGA, a training-free legal retrieval framework that injects structured applicability-oriented cues into dense retrieval. SAGA constructs a Case Applicability Frame (CAF) from user-side dialogue context to summarize dispute issues, core facts, and missing facts, and uses an offline Article Applicability Frame (AAF) to represent statute-side issue tags, prerequisites, legal effects, and evidence cues. It combines raw semantic and structural applicability streams through late fusion. Experiments on two Chinese statute retrieval benchmarks, LexRAG and STARD, show that SAGA improves over strong sparse, dense, and LLM-enhanced baselines under a unified full-corpus protocol. SAGA yields statistically significant gains on the conversational LexRAG benchmark and more modest gains on STARD over the strongest dense baseline, improving nDCG@10 from 0.3504 to 0.3696 and from 0.5862 to 0.5940, respectively. These results suggest that structured applicability-oriented cues provide useful retrieval signals beyond raw semantic matching, especially in conversational legal retrieval.</abstract>
<identifier type="citekey">lv-etal-2026-saga</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.702/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>16207</start>
<end>16226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAGA: Structured Applicability-Guided Alignment for Conversational Legal Retrieval
%A Lv, Xinxuan
%A Li, Minghan
%A Zhou, Guodong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F lv-etal-2026-saga
%X Conversational legal retrieval requires identifying statutes that are better aligned with a user’s case context, even when relevant facts are revealed incrementally and incompletely across dialogue turns. Sparse and dense retrievers may return semantically related statutes that are poorly matched to these factual conditions. We propose SAGA, a training-free legal retrieval framework that injects structured applicability-oriented cues into dense retrieval. SAGA constructs a Case Applicability Frame (CAF) from user-side dialogue context to summarize dispute issues, core facts, and missing facts, and uses an offline Article Applicability Frame (AAF) to represent statute-side issue tags, prerequisites, legal effects, and evidence cues. It combines raw semantic and structural applicability streams through late fusion. Experiments on two Chinese statute retrieval benchmarks, LexRAG and STARD, show that SAGA improves over strong sparse, dense, and LLM-enhanced baselines under a unified full-corpus protocol. SAGA yields statistically significant gains on the conversational LexRAG benchmark and more modest gains on STARD over the strongest dense baseline, improving nDCG@10 from 0.3504 to 0.3696 and from 0.5862 to 0.5940, respectively. These results suggest that structured applicability-oriented cues provide useful retrieval signals beyond raw semantic matching, especially in conversational legal retrieval.
%U https://aclanthology.org/2026.emnlp-main.702/
%P 16207-16226
Markdown (Informal)
[SAGA: Structured Applicability-Guided Alignment for Conversational Legal Retrieval](https://aclanthology.org/2026.emnlp-main.702/) (Lv et al., EMNLP 2026)
ACL