← Search

Xiaoying Song

5 accepted papers

2025

A Dynamic Fusion Model for Consistent Crisis Response

EMNLP 2025

In response to the urgent need for effective communication with crisis-affected populations, automated responses driven by language models have been proposed to assist in crisis communications. A critical yet often overlooked factor is the consistency of response style, which could affect the trust

Cited by 0SourcePDFScholar
2025

Assessing the Human Likeness of AI-Generated Counterspeech

COLING 2025main

Counterspeech is a targeted response to counteract and challenge abusive or hateful content. It effectively curbs the spread of hatred and fosters constructive online communication. Previous studies have proposed different strategies for automatically generated counterspeech. Evaluations, however, f…

2025

Echoes of Discord: Forecasting Hater Reactions to Counterspeech

NAACL 2025findings

Hate speech (HS) erodes the inclusiveness of online users and propagates negativity and division. Counterspeech has been recognized as a way to mitigate the harmful consequences. While some research has investigated the impact of user-generated counterspeech on social media platforms, few have exami…

2025

Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL

EMNLP 2025

Health misinformation spreading online poses a significant threat to public health. Researchers have explored methods for automatically generating counterspeech to health misinformation as a mitigation strategy. Existing approaches often produce uniform responses, ignoring that the health literacy l

Cited by 0SourcePDFScholar
2024

Outcome-Constrained Large Language Models for Countering Hate Speech

EMNLP 2024main

Automatic counterspeech generation methods have been developed to assist efforts in combating hate speech. Existing research focuses on generating counterspeech with linguistic attributes such as being polite, informative, and intent-driven. However, the real impact of counterspeech in online enviro…

Cited by 7SourcePDFScholar