STEB is a new benchmark of 96 datasets in 7 languages for evaluating style text embeddings on authorship, detection, and linguistic probing tasks.
Towards ecologically valid research on language user interfaces
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
The paper presents a threat model, taxonomy, and six-dimension measurement framework for AI sandboxes to clarify valid testing claims for safety, security, and regulatory assurance.
citing papers explorer
-
STEB: Style Text Embedding Benchmark
STEB is a new benchmark of 96 datasets in 7 languages for evaluating style text embeddings on authorship, detection, and linguistic probing tasks.
-
KTO: Model Alignment as Prospect Theoretic Optimization
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
-
AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
The paper presents a threat model, taxonomy, and six-dimension measurement framework for AI sandboxes to clarify valid testing claims for safety, security, and regulatory assurance.