@inproceedings{krishnakumar-etal-2026-rage,
title = "From Rage to Refusal : Using Social-Media Data to Steer Hostility-Related Affect in {LLM}s",
author = "Krishnakumar, Gayatri and
Puelma Touzel, Maximilian and
Yang, Zachary and
Godbout, Jean-Fran{\c{c}}ois and
Rabbany, Reihaneh",
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.46/",
pages = "795--817",
ISBN = "979-8-89176-476-7",
abstract = "Large language models (LLMs) are used as agents in social-media simulations, where behavioral fidelity may depend on preserving the affective intensity of real discourse. Using 3,692 unique Bluesky posts expanded into 14,768 activation records, we extract mild{--}strong affect directions in Qwen2.5 and Llama-3.1 Base and instruction-tuned checkpoints. Measured separation and reciprocal transfer to non-political hostility support a broader hostility-related feature rather than a uniquely partisan axis. In a six-prompt steering probe, checkpoints differ in their labeled hostile expression, refusal/deflection, and neutralization. Refusal/deflection includes substantive answers with disclaimers. Same-layer comparisons distinguish the hostility directions from a measured harmful-request contrast; removing that component changes behavioral counts non-uniformly and does not consistently return them to baseline. These descriptive results illustrate a representation{--}expression gap and motivate downstream fidelity audits."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnakumar-etal-2026-rage">
<titleInfo>
<title>From Rage to Refusal : Using Social-Media Data to Steer Hostility-Related Affect in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gayatri</namePart>
<namePart type="family">Krishnakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Puelma Touzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-François</namePart>
<namePart type="family">Godbout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reihaneh</namePart>
<namePart type="family">Rabbany</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 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</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">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are used as agents in social-media simulations, where behavioral fidelity may depend on preserving the affective intensity of real discourse. Using 3,692 unique Bluesky posts expanded into 14,768 activation records, we extract mild–strong affect directions in Qwen2.5 and Llama-3.1 Base and instruction-tuned checkpoints. Measured separation and reciprocal transfer to non-political hostility support a broader hostility-related feature rather than a uniquely partisan axis. In a six-prompt steering probe, checkpoints differ in their labeled hostile expression, refusal/deflection, and neutralization. Refusal/deflection includes substantive answers with disclaimers. Same-layer comparisons distinguish the hostility directions from a measured harmful-request contrast; removing that component changes behavioral counts non-uniformly and does not consistently return them to baseline. These descriptive results illustrate a representation–expression gap and motivate downstream fidelity audits.</abstract>
<identifier type="citekey">krishnakumar-etal-2026-rage</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.46/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>795</start>
<end>817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Rage to Refusal : Using Social-Media Data to Steer Hostility-Related Affect in LLMs
%A Krishnakumar, Gayatri
%A Puelma Touzel, Maximilian
%A Yang, Zachary
%A Godbout, Jean-François
%A Rabbany, Reihaneh
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F krishnakumar-etal-2026-rage
%X Large language models (LLMs) are used as agents in social-media simulations, where behavioral fidelity may depend on preserving the affective intensity of real discourse. Using 3,692 unique Bluesky posts expanded into 14,768 activation records, we extract mild–strong affect directions in Qwen2.5 and Llama-3.1 Base and instruction-tuned checkpoints. Measured separation and reciprocal transfer to non-political hostility support a broader hostility-related feature rather than a uniquely partisan axis. In a six-prompt steering probe, checkpoints differ in their labeled hostile expression, refusal/deflection, and neutralization. Refusal/deflection includes substantive answers with disclaimers. Same-layer comparisons distinguish the hostility directions from a measured harmful-request contrast; removing that component changes behavioral counts non-uniformly and does not consistently return them to baseline. These descriptive results illustrate a representation–expression gap and motivate downstream fidelity audits.
%U https://aclanthology.org/2026.blackboxnlp-1.46/
%P 795-817
Markdown (Informal)
[From Rage to Refusal : Using Social-Media Data to Steer Hostility-Related Affect in LLMs](https://aclanthology.org/2026.blackboxnlp-1.46/) (Krishnakumar et al., BlackboxNLP 2026)
ACL