mlsanityData to 7 Oct 2026

CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks

arXiv 2409.03381 ↗First posted 5 Sep 2024cs.CL cs.AIcited by 5

On the map: Synthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training

Abstract (arXiv)

Cognitive psychology investigates perception, attention, memory, language, problem-solving, decision-making, and reasoning. Kahneman's dual-system theory elucidates the human decision-making process, distinguishing between the rapid, intuitive System 1 and the deliberative, rational System 2. Recent advancements have positioned large language Models (LLMs) as formidable tools nearing human-level proficiency in various cognitive tasks. Nonetheless, the presence of a dual-system framework analogous to human cognition in LLMs remains unexplored. This study introduces the CogniDual Framework for LLMs (CFLLMs), designed to assess whether LLMs can, through self-training, evolve from deliberate deduction to intuitive responses, thereby emulating the human process of acquiring and mastering new information. Our findings reveal the cognitive mechanisms behind LLMs' response generation, enhancing our understanding of their capabilities in cognitive psychology. Practically, self-trained models can provide faster responses to certain queries, reducing computational demands during inference.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 21 of its 36 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

21 of 36 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  11. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  12. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
9 more
  1. 2022Large Language Models Are Reasoning Teacherscited by 318
  2. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 249
  3. 2020ReClor: A Reading Comprehension Dataset Requiring Logical Reasoningcited by 211
  4. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
  5. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  6. 2023Task Contamination: Language Models May Not Be Few-Shot Anymorecited by 98
  7. 2022In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Modelscited by 36
  8. 2023Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classificationcited by 17
  9. 2024BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinkingcited by 14
  2. 2025Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarizationcited by 6
  3. 2024Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Frameworkcited by 4
  4. 2025Can an Easy-to-Hard Curriculum Make Reasoning Emerge in Small Language Models? Evidence from a Four-Stage Curriculum on GPT-2cited by 1
  5. 2026Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detectioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models
  2. 2026Understanding Large Language Models
  3. 2023Turning large language models into cognitive models
  4. 2023Mind meets machine: Unravelling GPT-4's cognitive psychology
  5. 2025Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory
  6. 2022Thinking Fast and Slow in Large Language Models
  7. 2025On the Thinking-Language Modeling Gap in Large Language Models
  8. 2025Giving AI Personalities Leads to More Human-Like Reasoning