Zero-dimensional persistent homology on transformer layer hidden states yields three descriptors per layer whose concatenation improves ill-posedness classification and enables topology-conditioned activation steering across three LLMs.
Blowfish: Topological and statistical signatures for quantifying ambiguity in semantic search.arXiv preprint arXiv:2406.07990, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs
Zero-dimensional persistent homology on transformer layer hidden states yields three descriptors per layer whose concatenation improves ill-posedness classification and enables topology-conditioned activation steering across three LLMs.