Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
Linguistic Regularities in Continuous Space Word Representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Stable personality vectors in LLMs function as intrinsic guardrails, with ablation increasing emergent misalignment above 40% and amplification reducing it below 3%, enabling zero-shot transfer from aligned to corrupted models.
Sentiment is represented as a single linear direction in LLM activation space that is causally relevant across tasks and is summarized at punctuation and names in addition to charged words.
citing papers explorer
-
Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance
Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
-
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Stable personality vectors in LLMs function as intrinsic guardrails, with ablation increasing emergent misalignment above 40% and amplification reducing it below 3%, enabling zero-shot transfer from aligned to corrupted models.
-
Linear Representations of Sentiment in Large Language Models
Sentiment is represented as a single linear direction in LLM activation space that is causally relevant across tasks and is summarized at punctuation and names in addition to charged words.