paper
Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
paperactiveprovisional
reasoning-as-pattern-matching-shared-mechanisms-in-human-and-llm-everyday-reasoning-161ffc6c·1 events·first seen 5d agoAliases: Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
More like this (12)
Reasoning Language ModelsAgentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningReasoning in Memory (RiM)Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning ModelsPragmatic ReasoningWatch, Remember, Reason: Human-View Video Understanding with MLLMsReasoning ImitationLarge Reasoning ModelsBeyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning ModelsLong-context Reasoning Benchmarkslatent reasoningWhen the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Recent events (1)
Study finds shared pattern-matching mechanisms underlie both human and LLM everyday reasoning errors
A new arXiv paper evaluates human participants and 25 LLMs on commonsense causal reasoning tasks, finding similar error patterns in both groups. The authors identify specific attention heads driving LLM responses that implement pattern-matching, and show these heads can predict human reasoning errors caused by superficially irrelevant prompt details. The findings challenge the common assumption that human reasoning relies on principled abstract world models while LLMs merely pattern-match, suggesting both may share a more unified cognitive mechanism.