@inproceedings{chen-etal-2026-hate,
title = "Hate Is More Than What We See: Precedent-Guided Structured Reasoning for Hateful Video Detection",
author = "Chen, Junyi and
Liu, Qian and
Sun, Jing and
Zhang, Yi",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1336/",
pages = "28320--28344",
ISBN = "979-8-89176-462-0",
abstract = "Hateful video detection is a critical task for maintaining a healthy online ecosystem. However, existing methods are limited in their ability to deeply comprehend hateful semantics in videos and lack an effective mechanism for handling ambiguous cases near the decision boundary, making implicit hate detection particularly challenging. In this work, we address these limitations through both internal meaning formation from the video itself and external evidence consultation, and propose a novel framework, HATELENS. Internally, we design perception-to-cognition reasoning to perceive multimodal cues, perform cognition-level deep understanding, and progressively construct structured hateful meaning. Externally, we propose a test-time retrieval and adaptation mechanism to provide richer local evidence to help disambiguate implicit hate, which operates on fused multimodal representations to exploit annotated precedents. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance, with macro-precision improvements of up to 16{\%}. The code of our project is available at \url{https://github.com/JunyiChen-ai/HATELENS}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-hate">
<titleInfo>
<title>Hate Is More Than What We See: Precedent-Guided Structured Reasoning for Hateful Video Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Hateful video detection is a critical task for maintaining a healthy online ecosystem. However, existing methods are limited in their ability to deeply comprehend hateful semantics in videos and lack an effective mechanism for handling ambiguous cases near the decision boundary, making implicit hate detection particularly challenging. In this work, we address these limitations through both internal meaning formation from the video itself and external evidence consultation, and propose a novel framework, HATELENS. Internally, we design perception-to-cognition reasoning to perceive multimodal cues, perform cognition-level deep understanding, and progressively construct structured hateful meaning. Externally, we propose a test-time retrieval and adaptation mechanism to provide richer local evidence to help disambiguate implicit hate, which operates on fused multimodal representations to exploit annotated precedents. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance, with macro-precision improvements of up to 16%. The code of our project is available at https://github.com/JunyiChen-ai/HATELENS.</abstract>
<identifier type="citekey">chen-etal-2026-hate</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1336/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>28320</start>
<end>28344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hate Is More Than What We See: Precedent-Guided Structured Reasoning for Hateful Video Detection
%A Chen, Junyi
%A Liu, Qian
%A Sun, Jing
%A Zhang, Yi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F chen-etal-2026-hate
%X Hateful video detection is a critical task for maintaining a healthy online ecosystem. However, existing methods are limited in their ability to deeply comprehend hateful semantics in videos and lack an effective mechanism for handling ambiguous cases near the decision boundary, making implicit hate detection particularly challenging. In this work, we address these limitations through both internal meaning formation from the video itself and external evidence consultation, and propose a novel framework, HATELENS. Internally, we design perception-to-cognition reasoning to perceive multimodal cues, perform cognition-level deep understanding, and progressively construct structured hateful meaning. Externally, we propose a test-time retrieval and adaptation mechanism to provide richer local evidence to help disambiguate implicit hate, which operates on fused multimodal representations to exploit annotated precedents. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance, with macro-precision improvements of up to 16%. The code of our project is available at https://github.com/JunyiChen-ai/HATELENS.
%U https://aclanthology.org/2026.findings-emnlp.1336/
%P 28320-28344
Markdown (Informal)
[Hate Is More Than What We See: Precedent-Guided Structured Reasoning for Hateful Video Detection](https://aclanthology.org/2026.findings-emnlp.1336/) (Chen et al., Findings 2026)
ACL