LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
Scaling up active testing to large language models.arXiv preprint arXiv:2508.09093
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
SELECT-LLM is the first active model selection framework for LLMs that uses expected information gain from pairwise output similarities to minimize required annotations, reporting up to 84.78% cost reduction across 23 datasets and 156 models.
Proposes surrogate semantic entropy stratification followed by approximate Neyman allocation for active testing of LLMs on generative benchmarks, reporting up to 28% MSE reduction and 22.9% average budget savings versus uniform sampling.
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.
Fine-tuned multilingual LLMs achieve top shared-task scores on financial causality extraction in English and Spanish.
citing papers explorer
-
Prediction-Powered Active Testing
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.