mlsanityData to 7 Oct 2026

From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning

arXiv 2310.18364 ↗First posted 24 Oct 2023cs.CL cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Pre-trained language models (PLMs) have shown impressive performance in various language tasks. However, they are prone to spurious correlations, and often generate illusory information. In real-world applications, PLMs should justify decisions with formalized, coherent reasoning chains, but this challenge remains under-explored. Cognitive psychology theorizes that humans are capable of utilizing fast and intuitive heuristic thinking to make decisions based on past experience, then rationalizing the decisions through slower and deliberative analytic reasoning. We incorporate these interlinked dual processes in fine-tuning and in-context learning with PLMs, applying them to two language understanding tasks that require coherent physical commonsense reasoning. We show that our proposed Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions, yielding state-of-the-art results on Tiered Reasoning for Intuitive Physics (TRIP). We also find that this improved coherence is a direct result of more faithful attention to relevant language context in each step of reasoning. Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 33 of its 50 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

33 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov

Other references · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  8. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  9. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  10. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  11. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  12. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
20 more
  1. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  2. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  3. 2021Explaining Answers with Entailment Treescited by 148
  4. 2018Dissecting Contextual Word Embeddings: Architecture and Representationcited by 146
  5. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  6. 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
  7. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 75
  8. 2020Thinking Fast and Slow in AIcited by 67
  9. 2018Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehensioncited by 62
  10. 2020Temporal Reasoning on Implicit Events from Distant Supervisioncited by 58
  11. 2021PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D Worldcited by 47
  12. 2017The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Taskcited by 39
  13. 2018NCRF++: An Open-source Neural Sequence Labeling Toolkitcited by 29
  14. 2017Verb Physics: Relative Physical Knowledge of Actions and Objectscited by 26
  15. 2021Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understandingcited by 19
  16. 2022Coalescing Global and Local Information for Procedural Text Understandingcited by 10
  17. 2022EvEntS ReaLM: Event Reasoning of Entity States via Language Modelscited by 7
  18. 2022Breakpoint Transformers for Modeling and Tracking Intermediate Beliefscited by 6
  19. 2021Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifierscited by 5
  20. 2022Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environmentscited by 5

Built on by

Cited by year

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

2 papers.

  1. 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypescited by 2
  2. 2024Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?cited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
  2. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  3. 2024First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning
  4. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking
  5. 2026Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision
  6. 2024Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models
  7. 2025From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models
  8. 2023Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners