# From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

arXiv: https://arxiv.org/abs/2406.03030 · HTML: https://mlsanity.com/paper/2406.03030/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Text Readability Assessment for Second Language Learners](https://mlsanity.com/paper/1906.07580/) (2019)
- [Linguistic Features for Readability Assessment](https://mlsanity.com/paper/2006.00377/) (2020)
- [Controlling Text Complexity in Neural Machine Translation](https://mlsanity.com/paper/1911.00835/) (2019)
- [SongNet: Rigid Formats Controlled Text Generation](https://mlsanity.com/paper/2004.08022/) (2020)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Experiments with Universal CEFR Classification](https://mlsanity.com/paper/1804.06636/) (2018)
- ["My Way of Telling a Story": Persona based Grounded Story Generation](https://mlsanity.com/paper/1906.06401/) (2019)
- [Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models](https://mlsanity.com/paper/2309.05454/) (2023)
- [Controlling Pre-trained Language Models for Grade-Specific Text Simplification](https://mlsanity.com/paper/2305.14993/) (2023)
- [Automatic Readability Assessment for Closely Related Languages](https://mlsanity.com/paper/2305.13478/) (2023)
- [Controlled Language Generation for Language Learning Items](https://mlsanity.com/paper/2211.15731/) (2022)
- [BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages](https://mlsanity.com/paper/2310.11584/) (2023)

## Built on by (most cited first, 15 of 15)

- [Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring](https://mlsanity.com/paper/2505.08351/) (2025)
- [Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance](https://mlsanity.com/paper/2503.04736/) (2025)
- [Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation](https://mlsanity.com/paper/2506.04072/) (2025)
- [Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL](https://mlsanity.com/paper/2509.01058/) (2025)
- [German4All -- A Dataset and Model for Readability-Controlled Paraphrasing in German](https://mlsanity.com/paper/2508.17973/) (2025)
- [RephQA: Evaluating Readability of Large Language Models in Public Health Question Answering](https://mlsanity.com/paper/2509.16360/) (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)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Uncovering Intention through LLM-Driven Code Snippet Description Generation](https://mlsanity.com/paper/2506.15453/) (2025)
- [Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification](https://mlsanity.com/paper/2602.07499/) (2026)
- [Controlling Language Difficulty in Dialogues with Linguistic Features](https://mlsanity.com/paper/2509.14545/) (2025)
- [CEFR-Annotated WordNet: LLM-Based Proficiency-Guided Semantic Database for Language Learning](https://mlsanity.com/paper/2510.18466/) (2025)
- [Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation](https://mlsanity.com/paper/2604.04450/) (2026)
- [Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification](https://mlsanity.com/paper/2604.05302/) (2026)

## Abstract (arXiv)

We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we evaluate the effectiveness of several key approaches for this task, including few-shot prompting, supervised finetuning, and reinforcement learning (RL), utilising both GPT-4 and open source alternatives like LLama2-7B and Mistral-7B. Our findings reveal a large performance gap between GPT-4 and the open source models when using prompt-based strategies. However, we show how to bridge this gap with a careful combination of finetuning and RL alignment. Our best model, CALM (CEFR-Aligned Language Model), surpasses the performance of GPT-4 and other strategies, at only a fraction of the cost. We further validate the quality of our results through a small-scale human study.