mlsanityData to 7 Oct 2026

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

arXiv 2406.03030 ↗First posted 5 Jun 2024cs.CL cs.LGcited by 15

Not on the map. Why?

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 20 of its 46 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

20 of 46 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  7. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  8. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 425
  9. 2019Text Readability Assessment for Second Language Learnerscited by 54
  10. 2020Linguistic Features for Readability Assessmentcited by 35
  11. 2019Controlling Text Complexity in Neural Machine Translationcited by 32
  12. 2020SongNet: Rigid Formats Controlled Text Generationcited by 25
8 more
  1. 2023Generating Summaries with Controllable Readability Levelscited by 24
  2. 2018Experiments with Universal CEFR Classificationcited by 17
  3. 2019"My Way of Telling a Story": Persona based Grounded Story Generationcited by 17
  4. 2023Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Modelscited by 17
  5. 2023Controlling Pre-trained Language Models for Grade-Specific Text Simplificationcited by 14
  6. 2023Automatic Readability Assessment for Closely Related Languagescited by 9
  7. 2022Controlled Language Generation for Language Learning Itemscited by 7
  8. 2023BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 6.

15 papers.

Sort:

By area:

  1. 2025Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoringcited by 6
  2. 2025Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliancecited by 5
  3. 2025Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversationcited by 3
  4. 2025Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RLcited by 3
  5. 2025German4All -- A Dataset and Model for Readability-Controlled Paraphrasing in Germancited by 2
  6. 2025RephQA: Evaluating Readability of Large Language Models in Public Health Question Answeringcited by 2
  7. 2026Classroom AI: Large Language Models as Grade-Specific Teacherscited by 2
  8. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  9. 2025Uncovering Intention through LLM-Driven Code Snippet Description Generationcited by 1
  10. 2026Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decodingcited by 1
  11. 2026Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplificationcited by 1
  12. 2025Controlling Language Difficulty in Dialogues with Linguistic Featurescited by 0
3 more
  1. 2025CEFR-Annotated WordNet: LLM-Based Proficiency-Guided Semantic Database for Language Learningcited by 0
  2. 2026Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generationcited by 0
  3. 2026Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM Users
  2. 2024A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
  3. 2024LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback
  4. 2024Aligning Large Language Models via Fine-grained Supervision
  5. 2025LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
  6. 2024The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
  7. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
  8. 2025REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback