mlsanityData to 14 Oct 2026

Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow

arXiv 2408.08651 ↗First posted 16 Aug 2024cs.CL cs.AIcited by 8

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

Abstract (arXiv)

Language models are known to absorb biases from their training data, leading to predictions driven by statistical regularities rather than semantic relevance. We investigate the impact of these biases on answer choice preferences in the Massive Multi-Task Language Understanding (MMLU) task. Our findings show that these biases are predictive of model preference and mirror human test-taking strategies even when chain of thought (CoT) reasoning is used. To address this issue, we introduce Counterfactual Prompting with Agnostically Primed CoT (APriCoT). We demonstrate that while Counterfactual Prompting with CoT alone is insufficient to mitigate bias, APriCoT effectively reduces the influence of base-rate probabilities while improving overall accuracy. Our results suggest that mitigating bias requires a slow thinking process which CoT alone may not provide as it tends to reinforce fast thinking model bias under some prompting methodologies. APriCoT is a step toward developing more robust and fair language models that can think slow.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 15 of its 22 references that are in the map. First posted on arXiv 16 Aug 2024.

Builds on

15 of 22 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought8 Mar
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
  3. 2023Why think step by step? Reasoning emerges from the locality of experience7 Apr
  4. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning15 Dec
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 9

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  2. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 337
  3. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  4. 2021Do language models learn typicality judgments from text?cited by 32
  5. 2024Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Modelscited by 20
  6. 2024Eliciting the Priors of Large Language Models using Iterated In-Context Learningcited by 19
  7. 2023Using Artificial Populations to Study Psychological Phenomena in Neural Modelscited by 8
  8. 2024Large Language Model Recall Uncertainty is Modulated by the Fan Effectcited by 7
  9. 2024The Base-Rate Effect on LLM Benchmark Performance: Disambiguating Test-Taking Strategies from Benchmark Performancecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Modelscited by 6
  2. 2025ARB: A Comprehensive Arabic Multimodal Reasoning Benchmarkcited by 4
  3. 2026Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QAcited by 3
  4. 2025LLMs as Agentic Cooperative Players in Multiplayer UNOcited by 0
  5. 2026ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cuescited by 0
  6. 2026Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertaintycited by 0
  7. 2026Adaptive Triggering for Bias Correction in LLM Reasoningcited by 0
  8. 2026Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create Morecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Unveiling Confirmation Bias in Chain-of-Thought Reasoning
  2. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
  3. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  4. 2024The Impact of Reasoning Step Length on Large Language Models
  5. 2023Towards Better Chain-of-Thought Prompting Strategies: A Survey
  6. 2025Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
  7. 2024Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
  8. 2025How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding