newsHacker NewsTrust 52 · CommunityPublished 4d agoLive · 4d ago
Knowledge Distillation of Black-Box Large Language Models
48points12comments
Covers
paperHow Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple MitigationpaperNuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Modelsglossary_termTransformerrepoengineering87/llm-atlasrepominimal-diffusion-lm
Covers (incoming)
paperWhen are likely answers right? On Sequence Probability and Correctness in LLMspaperScaling limit of the Random Language ModelpaperAB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question AnsweringpaperLittle Brains, Big Feats: Exploring Compact Language ModelspaperEfficient Retrieval-Augmented Generation via Token Co-occurrence GraphspaperGrounding LLM Reasoning under Incomplete Graph EvidencepaperThe Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodologyrepochrisliu298/awesome-on-policy-distillationrepochrisliu298/awesome-llm-unlearningpaperObject Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt OptimizationpaperEduArt: An educational-level benchmark for evaluating art history knowledge in large language modelsreponick7nlp/Awesome-LLM-On-Policy-Distillation
Related across the graph
repochrisliu298/awesome-llm-unlearningpaperLittle Brains, Big Feats: Exploring Compact Language ModelspaperObject Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimizationrepochrisliu298/awesome-on-policy-distillationpaperWhen are likely answers right? On Sequence Probability and Correctness in LLMsglossary_termTransformerrepominimal-diffusion-lmrepoengineering87/llm-atlaspaperAB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question AnsweringpaperGrounding LLM Reasoning under Incomplete Graph Evidencereponick7nlp/Awesome-LLM-On-Policy-DistillationpaperEfficient Retrieval-Augmented Generation via Token Co-occurrence GraphspaperEduArt: An educational-level benchmark for evaluating art history knowledge in large language modelspaperHow Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple MitigationpaperThe Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training MethodologypaperNuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language ModelspaperScaling limit of the Random Language Model