TALEC : Customized Business Evaluation Criteria

human preferences and achieves a correlation of over 80% with human judgments,

zero-shot and few-shot to make the judge model focus on more information.

allows users to flexibly set their own evaluation criteria, and uses in-context learning (ICL) to teach judge model these in-house criteria

Especially in specific application domains (e.g., to-business or to-customer service), in-house evaluation criteria have to meet not only general standards (correctness, helpfulness and creativity, etc.) but also specific needs of customers and business security requirements at the same time, making the evaluation more difficult