Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
A Dynamic Fusion Model for Consistent Crisis Response
Published in The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), 2025
We introduce a dynamic fusion framework that integrates multiple LLMs to generate consistent, high-quality crisis responses across professionalism, actionability, and relevance dimensions.
Recommended citation: Song, Xiaoying, Anirban Saha Anik, Eduardo Blanco, Vanessa Frias-Martinez, and Lingzi Hong. "A Dynamic Fusion Model for Consistent Crisis Response." arXiv preprint arXiv:2509.01053 (2025).
Download Paper
Dynamic Fusion of Large Language Models for Crisis Communication
Published in Proceedings of the International ISCRAM Conference, 2025
We propose a dynamic fusion framework using multiple LLMs to generate high-quality, real-time responses in crisis scenarios on social media.
Recommended citation: Hong, L., Song, X., Saha Anik, A., Frías-Martínez, V. (2025). "Dynamic Fusion of Large Language Models for Crisis Communication." Proceedings of the International ISCRAM Conference. DOI: https://doi.org/10.59297/nqysjq45.
Download Paper | Download Slides
Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
Published in The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025 Findings) – Accepted, 2025
We propose a Controlled-Literacy framework that integrates Retrieval-Augmented Generation (RAG) and Reinforcement Learning (RL) to generate counterspeech tailored to different health literacy levels.
Recommended citation: Song, Xiaoying, Anirban Saha Anik, Dibakar Barua, Pengcheng Luo, Junhua Ding, and Lingzi Hong. "Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL." arXiv preprint arXiv:2509.01058 (2025)..
Download Paper
Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation
Published in Conference on Language Models (COLM 2025) – Accepted, 2025
A multi-agent LLM framework that generates evidence-based counterspeech grounded in dynamic and static retrieval sources, achieving significant improvements over RAG baselines.
Recommended citation: Anirban Saha Anik, Xiaoying Song, Elliott Wang, Bryan Wang, Bengisu Yarimbas, Lingzi Hong. (2025). "Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation." Conference on Language Models (COLM 2025).
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.