mlsanityData to 7 Oct 2026

Multi-Objective Linguistic Control of Large Language Models

arXiv 2406.16229 ↗First posted 23 Jun 2024cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs), despite their breakthroughs on many challenging benchmark tasks, lean to generate verbose responses and lack the controllability of output complexity, which is usually preferred by human users in practice. In this paper, we study how to precisely control multiple linguistic complexities of LLM output by finetuning using off-the-shelf data. To this end, we propose multi-control tuning (MCTune), which includes multiple linguistic complexity values of ground-truth responses as controls in the input for instruction tuning. We finetune LLaMA2-7B on Alpaca-GPT4 and WizardLM datasets. Evaluations on widely used benchmarks demonstrate that our method does not only improve LLMs' multi-complexity controllability substantially but also retains or even enhances the quality of the responses as a side benefit.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 23 Jun 2024.

Builds on

27 of 40 references.

References · 27

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  7. 2023LIMA: Less Is More for Alignmentcited by 1,080
  8. 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 350
  9. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  10. 2023A Long Way to Go: Investigating Length Correlations in RLHFcited by 285
  11. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  12. 2023Pretraining Language Models with Human Preferencescited by 245
15 more
  1. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  2. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 147
  3. 2024Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuningcited by 134
  4. 2024ODIN: Disentangled Reward Mitigates Hacking in RLHFcited by 133
  5. 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuningcited by 85
  6. 2024Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuningcited by 57
  7. 2021Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Featurescited by 36
  8. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 33
  9. 2021UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysiscited by 28
  10. 2024Automated Data Curation for Robust Language Model Fine-Tuningcited by 27
  11. 2023Taming AI Bots: Controllability of Neural States in Large Language Modelscited by 22
  12. 2023LFTK: Handcrafted Features in Computational Linguisticscited by 19
  13. 2020Exploring the Value of Personalized Word Embeddingscited by 17
  14. 2023Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Modelscited by 16
  15. 2023PerPLM: Personalized Fine-tuning of Pretrained Language Models via Writer-specific Intermediate Learning and Promptscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillationcited by 14
  2. 2025Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editingcited by 2
  3. 2025Controlling Language Difficulty in Dialogues with Linguistic Featurescited by 0
  4. 2026One Model for All: Multi-Objective Controllable Language Modelscited by 0