mlsanityData to 7 Oct 2026

ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses

arXiv 2403.09131 ↗First posted 14 Mar 2024cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated efficacy in various linguistic applications, including question answering and controlled text generation. However, studies into their ability to switch between opposite styles of responses in professional domains remain underexplored. This study introduces a novel approach, named ProSwitch, which enables a language model to switch between professional and non-professional answers, by tuning and evaluating through the guidance of domain and style knowledge. ProSwitch unfolds in three phases: LLM-augmented preparation to collect domain knowledge and QA pairs, instruction tuning to optimize LLMs with multiple levels of knowledge, and comprehensive evaluation to assess both style discrimination and reference-based quality of the generated text. Comparative analysis of ProSwitch against general and specialized LLMs reveals that our approach outperforms baselines in switching between professional and non-professional responses.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

38 of 58 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  7. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  8. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  10. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  11. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  12. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
26 more
  1. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  2. 2022A Survey on In-context Learningcited by 717
  3. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  4. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  5. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  6. 2020MedDialog: Two Large-scale Medical Dialogue Datasetscited by 157
  7. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  8. 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
  9. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  10. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  11. 2019Evaluating Style Transfer for Textcited by 59
  12. 2020Controllable Text Simplification with Explicit Paraphrasingcited by 53
  13. 2023ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfercited by 49
  14. 2021Aspect-Controllable Opinion Summarizationcited by 47
  15. 2022A Causal Lens for Controllable Text Generationcited by 45
  16. 2023LMDX: Language Model-based Document Information Extraction and Localizationcited by 37
  17. 2022A Distributional Lens for Multi-Aspect Controllable Text Generationcited by 33
  18. 2019The TechQA Datasetcited by 29
  19. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  20. 2024Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answeringcited by 18
  21. 2020Contextual Text Style Transfercited by 16
  22. 2022Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysiscited by 16
  23. 2021Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfercited by 5
  24. 2023Medical Question Summarization with Entity-driven Contrastive Learningcited by 5
  25. 2021Syntax Matters! Syntax-Controlled in Text Style Transfercited by 3
  26. 2023Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Trainingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2025C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generationcited by 1
  2. 2026Unsupervised Text Style Transfer for Controllable Intensitycited by 1