Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing
This addresses safety and transparency concerns for adopting LMs in critical domains like environmental policy, though it is incremental in applying existing methods to a new application.
The paper tackles the challenge of responsibly leveraging language models in real-world tasks by proposing a framework for LM-powered subroutines that are auditable and improvable with human feedback, and it demonstrates this in public comment processing with quantitative evaluation against historical ground-truth data.
The advent of language models (LMs) has the potential to dramatically accelerate tasks that may be cast to text-processing; however, real-world adoption is hindered by concerns regarding safety, explainability, and bias. How can we responsibly leverage LMs in a transparent, auditable manner -- minimizing risk and allowing human experts to focus on informed decision-making rather than data-processing or prompt engineering? In this work, we propose a framework for declaring statically typed, LM-powered subroutines (i.e., callable, function-like procedures) for use within conventional asynchronous code -- such that sparse feedback from human experts is used to improve the performance of each subroutine online (i.e., during use). In our implementation, all LM-produced artifacts (i.e., prompts, inputs, outputs, and data-dependencies) are recorded and exposed to audit on demand. We package this framework as a library to support its adoption and continued development. While this framework may be applicable across several real-world decision workflows (e.g., in healthcare and legal fields), we evaluate it in the context of public comment processing as mandated by the 1969 National Environmental Protection Act (NEPA): Specifically, we use this framework to develop "CommentNEPA," an application that compiles, organizes, and summarizes a corpus of public commentary submitted in response to a project requiring environmental review. We quantitatively evaluate the application by comparing its outputs (when operating without human feedback) to historical ``ground-truth'' data as labelled by human annotators during the preparation of official environmental impact statements.