Work

Counterspeech Generation using Small Language Models

Year: 2026

Type: conference-paper

Abstract: Counterspeech offers a potential way to tackle harmful content online without restricting freedom of expression.This work explores counterspeech generation using small language models (SLMs) as lightweight and costeffective alternatives to large language models.We evaluate SLMs ranging from 100 million to 3 billion parameters using simple prompting strategies as well as fine-tuning, combining automatic and robust human evaluations.Our findings demonstrate that small language models have potential to generate relevant, coherent, and high-quality counterspeech, suggesting their potential suitability for efficient and responsible deployments.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-srw.52

Authors: Abubakar Sadiq Muhammad, Simona Frenda, Gavin Abercrombie

Institution: Heriot-Watt University

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Engineering and Physical Sciences Research Council

Award: Equally Safe Online