Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Dec 202419922001200920172026
1 result for “DSPy”
A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluationcs.CL

Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.

problem Aligning LLM evaluation metrics with human annotations.
method Comparative analysis of five teleprompter algorithms within the DSPy framework.
result Certain teleprompters outperform others in detecting hallucinations.
DSPyteleprompterLLMalignmenthallucination
2024-12-19abs ↗pdf ↗