newsGoogle News — LLMTrust 62 · AggregatorPublished 8d agoLive · 7d ago
Understanding large language models demands distinguishing human projection from machine cognition - Nature
Understanding large language models demands distinguishing human projection from machine cognition Nature
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) · 60%Understanding Large Language Models →
- PossiblePossibly related (embedding) · 56%Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates →
- PossiblePossibly related (embedding) · 55%Furyton/awesome-language-model-analysis →
- PossiblePossibly related (embedding) · 55%Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models →
- PossiblePossibly related (embedding) · 54%Language Models as Measurement Apparatus for Culture →
- PossiblePossibly related (embedding) · 47%Linear representations of grammaticality in neural language models →
- PossiblePossibly related (embedding) · 47%HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning →
- PossiblePossibly related (embedding) · 53%Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery →
Covers
paperUnderstanding Large Language ModelspaperConversable Complexity: Agentic LLM Collectives as Interpretable SubstratesrepoFuryton/awesome-language-model-analysispaperRepresentational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language ModelspaperLanguage Models as Measurement Apparatus for Culture
Covers (incoming)
paperLinear representations of grammaticality in neural language modelspaperHoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven ReasoningpaperBefore the Action: Benchmarking LLMs on Prospective Hypothesis DiscoverypaperHow Much Human Label Variation Does Formal Semantic Structure Explain?: Group-Level Effects and Item-Level Ceilings in NLIpaperIt's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of BeliefpaperThe Two-Process Theory of Machine Self-ReportpaperGotta Catch them all: the modes of Sycophancypapersurprisal is Not a TheorypaperExposure is Optional: Learning Unlike Coordination in Language ModelspaperThe Maskability Index: Predicting Task-Objective Alignment in Pretrained Language ModelspaperEmergent Misalignment Recruits a Pre-existing Persona Subspace
Related across the graph
paperHow Much Human Label Variation Does Formal Semantic Structure Explain?: Group-Level Effects and Item-Level Ceilings in NLIpaperEmergent Misalignment Recruits a Pre-existing Persona SubspacepaperBefore the Action: Benchmarking LLMs on Prospective Hypothesis DiscoverypaperExposure is Optional: Learning Unlike Coordination in Language ModelspaperIt's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of BeliefpaperHoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven ReasoningpaperRepresentational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language ModelspaperThe Two-Process Theory of Machine Self-ReportpaperLanguage Models as Measurement Apparatus for CulturepaperGotta Catch them all: the modes of SycophancypaperUnderstanding Large Language ModelspaperConversable Complexity: Agentic LLM Collectives as Interpretable SubstratespaperThe Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Modelspapersurprisal is Not a TheorypaperLinear representations of grammaticality in neural language modelsrepoFuryton/awesome-language-model-analysis