PromptSR
An LLM experimentation tool designed for systematic review literature screening. It supports prompt engineering experiments, experiment management, and results analysis, and is intended for use alongside the SRBench benchmark framework.
Timeline (last 90 days)
A paper proposes SRBench, a benchmark framework targeting the screening phase of systematic reviews, along with a companion experimental tool PromptSR for evaluating large language models on literature screening tasks.
PromptSR provides three capabilities — prompt experimentation, experiment management, and result analysis — to support LLM-based screening experiments.
The paper presents an application case demonstrating how SRBench and PromptSR work together.
All Facts (3)
PromptSR provides three capabilities — prompt experimentation, experiment management, and result analysis — to support LLM-based screening experiments.
50%UnverifiedThe paper presents an application case demonstrating how SRBench and PromptSR work together.
50%UnverifiedA paper proposes SRBench, a benchmark framework targeting the screening phase of systematic reviews, along with a companion experimental tool PromptSR for evaluating large language models on literature screening tasks.
50%