# Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing

arXiv: https://arxiv.org/abs/2507.08109 · HTML: https://mlsanity.com/paper/2507.08109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models](https://mlsanity.com/paper/2203.07281/) (2022)
- [Simple regret for infinitely many armed bandits](https://mlsanity.com/paper/1505.04627/) (2015)
- [Efficient Prompt Optimization Through the Lens of Best Arm Identification](https://mlsanity.com/paper/2402.09723/) (2024)
- [Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization](https://mlsanity.com/paper/2406.15708/) (2024)
- [A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions](https://mlsanity.com/paper/2409.16430/) (2024)
- [Maillard Sampling: Boltzmann Exploration Done Optimally](https://mlsanity.com/paper/2111.03290/) (2021)
- [Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems](https://mlsanity.com/paper/2505.13546/) (2025)
- [SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback](https://mlsanity.com/paper/2505.19514/) (2025)
- [Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)](https://mlsanity.com/paper/2411.08469/) (2024)

## Abstract (arXiv)

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.