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

• URL: http://arxiv.org/abs/2509.01058v3
• Date: Mon, 22 Sep 2025 15:44:51 GMT
• Title: Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
• Authors: Xiaoying Song, Anirban Saha Anik, Dibakar Barua, Pengcheng Luo, Junhua Ding, Lingzi Hong,
• Abstract summary: Health misinformation spreading online poses a significant threat to public health.<n>We propose a Controlled-Literacy framework to generate tailored counterspeech adapted to different health literacy levels.<n>We design a reward function incorporating subjective user preferences and objective readability-based rewards to optimize counterspeech to the target health literacy level.
• Score: 3.8227085010838344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• RephQA: Evaluating Readability of Large Language Models in Public Health Question Answering [22.172697706271535]
  Large Language Models (LLMs) hold promise in addressing complex medical problems.<n>A significant bottleneck in developing effective healthcare agents lies in the readability of LLM-generated responses.<n>We introduce RephQA, a benchmark for evaluating the readability of LLMs in public health question answering (QA)
  arXiv  Detail & Related papers  (2025-09-19T19:09:42Z)
• Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation [8.23209620713472]
  We propose a Multi-agent Retrieval-Augmented Framework to generate counterspeech against health misinformation.<n>Our approach integrates both static and dynamic evidence, ensuring that the generated counterspeech is relevant, well-grounded, and up-to-date.
  arXiv  Detail & Related papers  (2025-07-09T22:10:06Z)
• HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation [68.4316501012718]
  HealthGPT is a powerful Medical Large Vision-Language Model (Med-LVLM)<n>It integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm.
  arXiv  Detail & Related papers  (2025-02-14T00:42:36Z)
• Guiding IoT-Based Healthcare Alert Systems with Large Language Models [22.54714587190204]
  Healthcare alert systems (HAS) are undergoing rapid evolution, propelled by advancements in artificial intelligence (AI), Internet of Things (IoT) technologies, and increasing health consciousness. Despite significant progress, a fundamental challenge remains: balancing the accuracy of personalized health alerts with stringent privacy protection in HAS environments constrained by resources. We introduce a uniform framework, LLM-HAS, which incorporates Large Language Models (LLM) into HAS to significantly boost the accuracy, ensure user privacy, and enhance personalized health service.
  arXiv  Detail & Related papers  (2024-08-23T13:55:36Z)
• Retrieval Augmented Thought Process for Private Data Handling in Healthcare [53.89406286212502]
  We introduce the Retrieval-Augmented Thought Process (RATP) RATP formulates the thought generation of Large Language Models (LLMs) On a private dataset of electronic medical records, RATP achieves 35% additional accuracy compared to in-context retrieval-augmented generation for the question-answering task.
  arXiv  Detail & Related papers  (2024-02-12T17:17:50Z)
• Understanding Counterspeech for Online Harm Mitigation [12.104301755723542]
  Counterspeech offers direct rebuttals to hateful speech by challenging perpetrators of hate and showing support to targets of abuse. It provides a promising alternative to more contentious measures, such as content moderation and deplatforming. This paper systematically reviews counterspeech research in the social sciences and compares methodologies and findings with computer science efforts in automatic counterspeech generation.
  arXiv  Detail & Related papers  (2023-07-01T20:54:01Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• On Curating Responsible and Representative Healthcare Video Recommendations for Patient Education and Health Literacy: An Augmented Intelligence Approach [5.545277272908999]
  One in three U.S. adults use the Internet to diagnose or learn about a health concern. Health literacy divides can be exacerbated by algorithmic recommendations.
  arXiv  Detail & Related papers  (2022-07-13T01:54:59Z)
• Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition? [86.53044183309824]
  We study which factor leads to the success of self-supervised learning on speaker-related tasks. Our empirical results on the Voxceleb-1 dataset suggest that the benefit of SSL to SV task is from a combination of mask speech prediction loss, data scale, and model size.
  arXiv  Detail & Related papers  (2022-04-27T08:35:57Z)
• Speaker De-identification System using Autoencoders and Adversarial Training [58.720142291102135]
  We propose a speaker de-identification system based on adversarial training and autoencoders. Experimental results show that combining adversarial learning and autoencoders increase the equal error rate of a speaker verification system.
  arXiv  Detail & Related papers  (2020-11-09T19:22:05Z)
• Assessing the Severity of Health States based on Social Media Posts [62.52087340582502]
  We propose a multiview learning framework that models both the textual content as well as contextual-information to assess the severity of the user's health state. The diverse NLU views demonstrate its effectiveness on both the tasks and as well as on the individual disease to assess a user's health.
  arXiv  Detail & Related papers  (2020-09-21T03:45:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.