newsBAIR (Berkeley)Trust 88 · LabPublished 5mo agoLive · 1mo ago
Identifying Interactions at Scale for LLMs
Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpre
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownminimal-diffusion-lm →
- LinkedLinked via unknownagent-tools →
- LinkedLinked via unknownsentence-transformers/all-MiniLM-L6-v2 →
- LinkedLinked via unknownTransformer →
- LinkedLinked via unknownengineering87/llm-atlas →
- LinkedLinked via unknownFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond →
- LinkedLinked via unknownAttractor States Emerge in Multi-Turn LLM Conversations →
Covers
Covers (incoming)
repoengineering87/llm-atlaspaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path BeyondpaperRepresentational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language ModelspaperAttractor States Emerge in Multi-Turn LLM ConversationspaperHarnessing Textual Refusal Directions for Multimodal SafetypaperAttend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM InferencepaperCoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty EstimationpaperUnderstanding Large Language ModelspaperConversable Complexity: Agentic LLM Collectives as Interpretable Substratesrepojordanhubbard/nanolangpaperRobust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science SkepticismpaperWill Scaling Improve Social Simulation with LLMs?repoEmo-gml/Awesome-Mental-Health-LLMsrepoicarito/gtk-llm-chatrepoModelTC/LightLLMrepoAtomic-man007/Awesome_Multimodel_LLMrepomistval/yozakurarepoVectorPeak/LLM-Wikirepollmsresearch/llm-flashcardsrepobaidu-baige/LoongForgerepoyubol-bobo/Awesome-Multi-Turn-LLMspaperGroc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMsrepofkkarakurt/NerverepoNayjest/ai-microcorepaperMeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party MeetingspaperWhich Values Do LLMs Confuse? A Schwartz-Based Recognition Study
Related across the graph
glossary_termTransformerpaperGroc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMsrepominimal-diffusion-lmrepoengineering87/llm-atlaspaperRepresentational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Modelsrepobaidu-baige/LoongForgepaperCoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimationrepomistval/yozakurarepoicarito/gtk-llm-chatpaperHarnessing Textual Refusal Directions for Multimodal Safetymodelsentence-transformers/all-MiniLM-L6-v2paperAttractor States Emerge in Multi-Turn LLM ConversationsrepoEmo-gml/Awesome-Mental-Health-LLMsrepollmsresearch/llm-flashcardspaperAttend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM InferencepaperRobust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science SkepticismrepoNayjest/ai-microcorerepoyubol-bobo/Awesome-Multi-Turn-LLMspaperUnderstanding Large Language ModelspaperConversable Complexity: Agentic LLM Collectives as Interpretable SubstratesrepoModelTC/LightLLMpaperWhich Values Do LLMs Confuse? A Schwartz-Based Recognition StudyrepoAtomic-man007/Awesome_Multimodel_LLMpaperMeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party MeetingsrepoVectorPeak/LLM-WikipaperWill Scaling Improve Social Simulation with LLMs?repofkkarakurt/Nerverepojordanhubbard/nanolangpaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyondrepoagent-tools