Read original ↗

newsNature Machine IntelligenceTrust 88 · LabPublished 10d agoLive · 8d ago

Implicit-bias-like patterns in reasoning models

Nature Machine Intelligence, Published online: 01 September 2026; doi:10.1038/s42256-026-01300-1 Lee and Lai study bias-like processing differences in large language reasoning models and find that, for most models, processing stereotypical information takes less computational effort than processing counter-stereotypical information.

Research Nature Machine Intelligence verified

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 55%Situation Perception: A Necessary Primitive to Artificial Superintelligence →
PossiblePossibly related (embedding) · 53%Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty →
PossiblePossibly related (embedding) · 53%From Plausible to Actionable: A Position on LLM Self-Explanations →
PossiblePossibly related (embedding) · 52%Do Large Language Models Hallucinate Electric Fata Morganas? →
PossiblePossibly related (embedding) · 52%When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness →
PossiblePossibly related (embedding) · 54%Typological Feature Prediction with Large Language Models: An In-Context Learning Approach →
PossiblePossibly related (embedding) · 48%Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness →

Covers

paperSituation Perception: A Necessary Primitive to Artificial Superintelligence paperThink-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty paperFrom Plausible to Actionable: A Position on LLM Self-Explanations paperDo Large Language Models Hallucinate Electric Fata Morganas?paperWhen Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

Covers (incoming)

paperTypological Feature Prediction with Large Language Models: An In-Context Learning Approach paperBeyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

Related across the graph

paperWhen Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness paperTypological Feature Prediction with Large Language Models: An In-Context Learning Approach paperBeyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness paperSituation Perception: A Necessary Primitive to Artificial Superintelligence paperFrom Plausible to Actionable: A Position on LLM Self-Explanations paperDo Large Language Models Hallucinate Electric Fata Morganas?paperThink-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty