mlsanityData to 7 Oct 2026

Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding

arXiv 2310.11721 ↗First posted 18 Oct 2023cs.CL cs.LGcited by 4

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex tasks into multi-step reasoning through intermediate steps in natural language form. Briefly, CoT enables LLMs to think step by step. However, although many Natural Language Understanding (NLU) tasks also require thinking step by step, LLMs perform less well than small-scale Masked Language Models (MLMs). To migrate CoT from LLMs to MLMs, we propose Chain-of-Thought Tuning (CoTT), a two-step reasoning framework based on prompt tuning, to implement step-by-step thinking for MLMs on NLU tasks. From the perspective of CoT, CoTT's two-step framework enables MLMs to implement task decomposition; CoTT's prompt tuning allows intermediate steps to be used in natural language form. Thereby, the success of CoT can be extended to NLU tasks through MLMs. To verify the effectiveness of CoTT, we conduct experiments on two NLU tasks: hierarchical classification and relation extraction, and the results show that CoTT outperforms baselines and achieves state-of-the-art performance.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 46 of its 51 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

46 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  2. 2022Large Language Models are Zero-Shot Reasoners24 May

Other references · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  8. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  9. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  10. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  11. 2019Language Models as Knowledge Bases?cited by 1,922
  12. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
32 more
  1. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  2. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  3. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  4. 2021GPT Understands, Toocited by 715
  5. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  6. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  7. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  8. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  9. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  10. 2021True Few-Shot Learning with Language Modelscited by 343
  11. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
  12. 2019Knowledge Enhanced Contextual Word Representationscited by 294
  13. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  14. 2021WARP: Word-level Adversarial ReProgrammingcited by 220
  15. 2023ChatGPT: Jack of all trades, master of nonecited by 204
  16. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
  17. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  18. 2017HDLTex: Hierarchical Deep Learning for Text Classificationcited by 105
  19. 2020Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classificationcited by 98
  20. 2020TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Taskcited by 96
  21. 2018SGM: Sequence Generation Model for Multi-label Classificationcited by 89
  22. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
  23. 2021Re-TACRED: Addressing Shortcomings of the TACRED Datasetcited by 73
  24. 2022Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classificationcited by 52
  25. 2023Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractorscited by 44
  26. 2022HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classificationcited by 31
  27. 2022AdaPrompt: Adaptive Model Training for Prompt-based NLPcited by 30
  28. 2021HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximizationcited by 25
  29. 2020Trust and Medical AI: The challenges we face and the expertise needed to overcome themcited by 21
  30. 2023Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enoughcited by 3
  31. 2023Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalizationcited by 2
  32. 2023Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causalitycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 2; 2026: 1.

4 papers.

  1. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
  2. 2023Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selectioncited by 5
  3. 2025A Partition Cover Approach to Tokenizationcited by 5
  4. 2026STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluatorcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization
  2. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  3. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning
  4. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  5. 2023CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
  6. 2024Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding
  7. 2024Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
  8. 2025CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs