CODEOFCONDUCT at Multilingual Counterspeech Generation: A Context-Aware Model for Robust Counterspeech Generation in Low-Resource Languages

TL;DR

This paper presents a context-aware multilingual counterspeech generation model that excels in low-resource languages, achieving state-of-the-art results in a shared task by leveraging simulated annealing and diverse evaluation metrics.

Contribution

The work introduces a novel, robust counterspeech generation model tailored for low-resource languages, demonstrating superior performance across multiple languages in a shared task setting.

Findings

Achieved first place for Basque, second for Italian, and top three for English and Spanish.

Outperformed existing models in low-resource language scenarios.

Provided comprehensive evaluation using traditional metrics and JudgeLM.

Abstract

This paper introduces a context-aware model for robust counterspeech generation, which achieved significant success in the MCG-COLING-2025 shared task. Our approach particularly excelled in low-resource language settings. By leveraging a simulated annealing algorithm fine-tuned on multilingual datasets, the model generates factually accurate responses to hate speech. We demonstrate state-of-the-art performance across four languages (Basque, English, Italian, and Spanish), with our system ranking first for Basque, second for Italian, and third for both English and Spanish. Notably, our model swept all three top positions for Basque, highlighting its effectiveness in low-resource scenarios. Evaluation of the shared task employs both traditional metrics (BLEU, ROUGE, BERTScore, Novelty) and JudgeLM based on LLM. We present a detailed analysis of our results, including an empirical evaluation of the model performance and comprehensive score distributions across evaluation metrics. This work contributes to the growing body of research on multilingual counterspeech generation, offering insights into developing robust models that can adapt to diverse linguistic and cultural contexts in the fight against online hate speech.