Saved in:
Bibliographic Details
Main Authors: Song, Xiaoying, Anik, Anirban Saha, Barua, Dibakar, Luo, Pengcheng, Ding, Junhua, Hong, Lingzi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.01058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918424212406272
author Song, Xiaoying
Anik, Anirban Saha
Barua, Dibakar
Luo, Pengcheng
Ding, Junhua
Hong, Lingzi
author_facet Song, Xiaoying
Anik, Anirban Saha
Barua, Dibakar
Luo, Pengcheng
Ding, Junhua
Hong, Lingzi
contents 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 level of the audience could affect the accessibility and effectiveness of counterspeech. We propose a Controlled-Literacy framework using retrieval-augmented generation (RAG) with reinforcement learning (RL) to generate tailored counterspeech adapted to different health literacy levels. In particular, we retrieve knowledge aligned with specific health literacy levels, enabling accessible and factual information to support generation. We design a reward function incorporating subjective user preferences and objective readability-based rewards to optimize counterspeech to the target health literacy level. Experiment results show that Controlled-Literacy outperforms baselines by generating more accessible and user-preferred counterspeech. This research contributes to more equitable and impactful public health communication by improving the accessibility and comprehension of counterspeech to health misinformation
format Preprint
id arxiv_https___arxiv_org_abs_2509_01058
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
Song, Xiaoying
Anik, Anirban Saha
Barua, Dibakar
Luo, Pengcheng
Ding, Junhua
Hong, Lingzi
Computation and Language
Artificial Intelligence
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 level of the audience could affect the accessibility and effectiveness of counterspeech. We propose a Controlled-Literacy framework using retrieval-augmented generation (RAG) with reinforcement learning (RL) to generate tailored counterspeech adapted to different health literacy levels. In particular, we retrieve knowledge aligned with specific health literacy levels, enabling accessible and factual information to support generation. We design a reward function incorporating subjective user preferences and objective readability-based rewards to optimize counterspeech to the target health literacy level. Experiment results show that Controlled-Literacy outperforms baselines by generating more accessible and user-preferred counterspeech. This research contributes to more equitable and impactful public health communication by improving the accessibility and comprehension of counterspeech to health misinformation
title Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.01058