English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Evaluating outputs of large language models (LLMs) is challenging, requiringmaking -- and making sense of -- many responses. Yet tools that go beyond basicprompting tend to require knowledge of programming APIs, focus on narrowdomains, or are closed-source. We present ChainForge, an open-source visualtoolkit for prompt engineering and on-demand hypothesis testing of textgeneration LLMs. ChainForge provides a graphical interface for comparison ofresponses across models and prompt variations. Our system was designed tosupport three tasks: model selection, prompt template design, and hypothesistesting (e.g., auditing). We released ChainForge early in its development anditerated on its design with academics and online users. Through in-lab andinterview studies, we find that a range of people could use ChainForge toinvestigate hypotheses that matter to them, including in real-world settings.We identify three modes of prompt engineering and LLM hypothesis testing:opportunistic exploration, limited evaluation, and iterative refinement.

ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing