Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systems
Javier Marín
When retrieval-augmented generation (RAG) systems hallucinate, what geometric trace does this leave in embedding space? We introduce the Semantic Grounding Index (SGI), defined as…
cs.AI2025
Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks
Javier Marín
We document empirical capability ceilings in decoder-only autoregressive language models across knowledge-intensive tasks. Systematic evaluation of OPT and Pythia model families (7…