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

arXiv: https://arxiv.org/abs/2509.01058 · HTML: https://mlsanity.com/paper/2509.01058/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [CORD-19: The COVID-19 Open Research Dataset](https://mlsanity.com/paper/2004.10706/) (2020)
- [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://mlsanity.com/paper/2404.07220/) (2024)
- [FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets](https://mlsanity.com/paper/2310.04793/) (2023)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications](https://mlsanity.com/paper/2408.10215/) (2024)
- [Language Models Hallucinate, but May Excel at Fact Verification](https://mlsanity.com/paper/2310.14564/) (2023)
- [Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation](https://mlsanity.com/paper/2403.14952/) (2024)
- [Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence](https://mlsanity.com/paper/2305.18265/) (2023)
- [Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments](https://mlsanity.com/paper/2406.09815/) (2024)
- [The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemic](https://mlsanity.com/paper/2011.05773/) (2020)
- [README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP](https://mlsanity.com/paper/2312.15561/) (2023)
- [Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?](https://mlsanity.com/paper/2312.02065/) (2023)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Know Your Audience: The benefits and pitfalls of generating plain language summaries beyond the "general" audience](https://mlsanity.com/paper/2403.04979/) (2024)
- [Outcome-Constrained Large Language Models for Countering Hate Speech](https://mlsanity.com/paper/2403.17146/) (2024)
- [A Study of Cyber Hate on Twitter with Implications for Social Media Governance Strategies](https://mlsanity.com/paper/1908.11732/) (2019)
- [Echoes of Discord: Forecasting Hater Reactions to Counterspeech](https://mlsanity.com/paper/2501.16235/) (2025)
- [Exploring the Readiness of Prominent Small Language Models for the Democratization of Financial Literacy](https://mlsanity.com/paper/2410.07118/) (2024)
- [Rescuing Counterspeech: A Bridging-Based Approach to Combating Misinformation](https://mlsanity.com/paper/2410.12699/) (2024)
- [Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning](https://mlsanity.com/paper/2410.17088/) (2024)
- [A Novel Dataset for Financial Education Text Simplification in Spanish](https://mlsanity.com/paper/2312.09897/) (2023)
- [Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning](https://mlsanity.com/paper/2401.15043/) (2024)

## Built on by (most cited first, 3 of 3)

- [Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs](https://mlsanity.com/paper/2605.24154/) (2026)
- [Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention](https://mlsanity.com/paper/2608.21721/) (2026)
- [Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness](https://mlsanity.com/paper/2610.00568/) (2026)

## Abstract (arXiv)

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