# Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent

arXiv: https://arxiv.org/abs/2608.04772 · HTML: https://mlsanity.com/paper/2608.04772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems](https://mlsanity.com/paper/1805.06966/) (2018)
- [ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning](https://mlsanity.com/paper/2502.14860/) (2025)
- [MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework](https://mlsanity.com/paper/2508.14880/) (2025)
- [Teaching Language Models To Gather Information Proactively](https://mlsanity.com/paper/2507.21389/) (2025)
- [From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage](https://mlsanity.com/paper/2504.16273/) (2025)

## Abstract (arXiv)

Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-restricted. We introduce Guideline-as-Oracle (GAO), which compiles American Academy of Ophthalmology guidance into a 70-row operational rule table and uses it as the sole source of instance-level supervision for 3,000 training dialogues, reserving human labeling for evaluation. Because converting rules into dialogues is itself a design problem, we catalog eight construction strategies, including cited-row tier assignment, one-fact boundary pairs, metadata-only repair, and label repair, and characterize the evidential status of each: labeling mechanism, null, confounded, or evaluated only as a package. Fine-tuning a 9B backbone on this corpus yields GAO-Triage, improving agreement with a 201-case operational reference from 61.7% to 74.1% (exact McNemar p=0.0046) and emergent-case recall from 9.5% to 69.0%; the gains persist across a second seed and patient simulator. None of the seven general-purpose systems we test dominates GAO-Triage on both metrics, and GAO-Triage requires no frontier model at inference time. Permuting label-dialogue assignments collapses the model to a constant-routine predictor, indicating that the signal lies in guideline-derived assignment rather than dialogue surface form. Label repair coincides with the disappearance of a late-training safety degradation.