@inproceedings{chu-etal-2026-dal,
title = "{DAL} Team at {P}sy{D}ef{D}etect: From Supervised Encoders to Hierarchical {LLM}-{RAG} for Psychological Defense Detection",
author = "Chu, Anh and
Tran, Luong and
Do, Dat and
Mai, Phuong and
Le, Quynh and
Can, Cat",
editor = "Gupta, Deepak and
Demner-Fushman, Dina",
booktitle = "Proceedings of the {B}io{NLP} 2026 (Shared Tasks)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-2.23/",
pages = "164--170",
ISBN = "979-8-89176-435-4",
abstract = "We propose a hierarchical framework for psychological defense mechanism detection in multi-turn dialogues, integrating large language models, retrieval-augmented generation, and heuristic calibration. Our approach decomposes prediction into coarse-to-fine reasoning stages and incorporates dialogue reconstruction, explanation-enhanced retrieval, and hybrid LLM{--}supervised filtering to address severe label imbalance and implicit, context-dependent labeling. Experiments on the PsyDefDetect dataset show that LLM-based RAG improves performance on minority and ambiguous classes, achieving a Macro F1 of 0.31, while also revealing persistent challenges in fine-grained discrimination of latent psychological constructs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2026-dal">
<titleInfo>
<title>DAL Team at PsyDefDetect: From Supervised Encoders to Hierarchical LLM-RAG for Psychological Defense Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luong</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phuong</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quynh</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cat</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the BioNLP 2026 (Shared Tasks)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-435-4</identifier>
</relatedItem>
<abstract>We propose a hierarchical framework for psychological defense mechanism detection in multi-turn dialogues, integrating large language models, retrieval-augmented generation, and heuristic calibration. Our approach decomposes prediction into coarse-to-fine reasoning stages and incorporates dialogue reconstruction, explanation-enhanced retrieval, and hybrid LLM–supervised filtering to address severe label imbalance and implicit, context-dependent labeling. Experiments on the PsyDefDetect dataset show that LLM-based RAG improves performance on minority and ambiguous classes, achieving a Macro F1 of 0.31, while also revealing persistent challenges in fine-grained discrimination of latent psychological constructs.</abstract>
<identifier type="citekey">chu-etal-2026-dal</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-2.23/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>164</start>
<end>170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAL Team at PsyDefDetect: From Supervised Encoders to Hierarchical LLM-RAG for Psychological Defense Detection
%A Chu, Anh
%A Tran, Luong
%A Do, Dat
%A Mai, Phuong
%A Le, Quynh
%A Can, Cat
%Y Gupta, Deepak
%Y Demner-Fushman, Dina
%S Proceedings of the BioNLP 2026 (Shared Tasks)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-435-4
%F chu-etal-2026-dal
%X We propose a hierarchical framework for psychological defense mechanism detection in multi-turn dialogues, integrating large language models, retrieval-augmented generation, and heuristic calibration. Our approach decomposes prediction into coarse-to-fine reasoning stages and incorporates dialogue reconstruction, explanation-enhanced retrieval, and hybrid LLM–supervised filtering to address severe label imbalance and implicit, context-dependent labeling. Experiments on the PsyDefDetect dataset show that LLM-based RAG improves performance on minority and ambiguous classes, achieving a Macro F1 of 0.31, while also revealing persistent challenges in fine-grained discrimination of latent psychological constructs.
%U https://aclanthology.org/2026.bionlp-2.23/
%P 164-170
Markdown (Informal)
[DAL Team at PsyDefDetect: From Supervised Encoders to Hierarchical LLM-RAG for Psychological Defense Detection](https://aclanthology.org/2026.bionlp-2.23/) (Chu et al., BioNLP 2026)
ACL