Converts impossibility theorems into architecture-dependent accuracy ceilings and design rules for transformers and other AI subfields, with the Deterministic Horizon measured at 19-31 across twelve models.
On the Fundamental Impossibility of Hallucination Control in Large Language Models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
AI security and alignment cannot achieve full robustness because any sufficiently powerful AI inherits incompleteness-style limitations from formal systems.
citing papers explorer
-
The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems
Converts impossibility theorems into architecture-dependent accuracy ceilings and design rules for transformers and other AI subfields, with the Deterministic Horizon measured at 19-31 across twelve models.
-
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
-
Robust AI Security and Alignment: A Sisyphean Endeavor?
AI security and alignment cannot achieve full robustness because any sufficiently powerful AI inherits incompleteness-style limitations from formal systems.