# Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?

arXiv: https://arxiv.org/abs/2312.02065 · HTML: https://mlsanity.com/paper/2312.02065/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Demographic Inference and Representative Population Estimates from Multilingual Social Media Data](https://mlsanity.com/paper/1905.05961/) (2019)

## Built on by (most cited first, 16 of 16)

- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://mlsanity.com/paper/2410.19109/) (2024)
- [Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts](https://mlsanity.com/paper/2405.09482/) (2024)
- [Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions](https://mlsanity.com/paper/2502.13780/) (2025)
- [Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?](https://mlsanity.com/paper/2402.14453/) (2024)
- [Free-text Rationale Generation under Readability Level Control](https://mlsanity.com/paper/2407.01384/) (2024)
- [Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL](https://mlsanity.com/paper/2509.01058/) (2025)
- [EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs](https://mlsanity.com/paper/2510.17389/) (2025)
- [Classroom AI: Large Language Models as Grade-Specific Teachers](https://mlsanity.com/paper/2601.06225/) (2026)
- [Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding](https://mlsanity.com/paper/2601.06403/) (2026)
- [Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation](https://mlsanity.com/paper/2509.19336/) (2025)
- [BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories](https://mlsanity.com/paper/2604.17008/) (2026)
- [Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation](https://mlsanity.com/paper/2608.29215/) (2026)

## Abstract (arXiv)

Large language models (LLMs) offer a range of new possibilities, including adapting the text to different audiences and their reading needs. But how well do they adapt? We evaluate the readability of answers generated by four state-of-the-art LLMs (commercial and open-source) to science questions when prompted to target different age groups and education levels. To assess the adaptability of LLMs to diverse audiences, we compare the readability scores of the generated responses against the recommended comprehension level of each age and education group. We find large variations in the readability of the answers by different LLMs. Our results suggest LLM answers need to be better adapted to the intended audience demographics to be more comprehensible. They underline the importance of enhancing the adaptability of LLMs in education settings to cater to diverse age and education levels. Overall, current LLMs have set readability ranges and do not adapt well to different audiences, even when prompted. That limits their potential for educational purposes.