November 2023 Summaries

Align AI, an early-stage startup, emphasizes the importance of embracing data privacy and security from the beginning. They achieved SOC2 certification by starting early, involving the entire organization in compliance efforts, leveraging platforms like Vanta for technical requirements, and collaborating with their auditor. The process was a valuable investment that demonstrated their commitment to data privacy and security.

The Align AI Research Review discusses recent research on using large language models (LLMs) as reference-free metrics for evaluating natural language generation (NLG). Microsoft Cognitive Services Research team proposed the G-EVAL framework, which employs complex LLMs with chain-of-thoughts and a form-filling strategy to evaluate NLG outputs. The G-EVAL framework consists of three main elements: prompt specification, chain-of-thought instructions, and a scoring function. An experiment was conducted to investigate whether LLMs exhibit a preference for their own outputs over human-written summaries. The findings suggest that while LLMs offer efficiency in handling large data volumes, they are not yet reliable enough to be the sole evaluators. Align AI recommends a hybrid approach integrating LLMs' computational power with human expert judgment for effective evaluation strategies.