Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering

Title: Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering
Authors: Helena Bonaldi; Greta Damo; Nicolás Benjamín Ocampo; Elena Cabrio; Serena Villata; Marco Guerini
Contributors: Bonaldi, Helena; Damo, Greta; Ocampo, Nicolás Benjamín; Cabrio, Elena; Villata, Serena; Guerini, Marco
Publication Year: 2024
Collection: Fondazione Bruno Kessler: CINECA IRIS
Description: The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated responses often lack the argumentative richness which characterises expert-produced counterspeech. In this work, we focus on two aspects of counterspeech generation to produce more cogent responses. First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations. Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate. By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions. Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations.
Document Type: conference object
Language: English
Relation: ispartofbook:Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing; 2024 Conference on Empirical Methods in Natural Language Processing; firstpage:3446; lastpage:3463; numberofpages:18; https://hdl.handle.net/11582/351788
DOI: 10.18653/v1/2024.emnlp-main.201
Availability: https://hdl.handle.net/11582/351788; https://doi.org/10.18653/v1/2024.emnlp-main.201; https://aclanthology.org/2024.emnlp-main.201/
Rights: info:eu-repo/semantics/openAccess ; license:Copyright dell'editore ; license uri:publisher
Accession Number: edsbas.DDF33043
Database: BASE