# Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?

arXiv: https://arxiv.org/abs/2605.29857 · HTML: https://mlsanity.com/paper/2605.29857/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 107 references that are in the map.
- First posted on arXiv 28 May 2026.

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

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews](https://mlsanity.com/paper/2306.12587/) (2023)
- [ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists](https://mlsanity.com/paper/2506.01241/) (2025)
- [CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling](https://mlsanity.com/paper/2410.21545/) (2024)
- [Automatic Analysis of Substantiation in Scientific Peer Reviews](https://mlsanity.com/paper/2311.11967/) (2023)
- [SedarEval: Automated Evaluation using Self-Adaptive Rubrics](https://mlsanity.com/paper/2501.15595/) (2025)
- [Learning to Judge: LLMs Designing and Applying Evaluation Rubrics](https://mlsanity.com/paper/2602.08672/) (2026)
- [The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors](https://mlsanity.com/paper/2509.04484/) (2025)
- [TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring](https://mlsanity.com/paper/2505.14577/) (2025)
- [Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity](https://mlsanity.com/paper/2309.06541/) (2023)
- [LLMCRIT: Teaching Large Language Models to Use Criteria](https://mlsanity.com/paper/2403.01069/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as expert preferences or organization-specific conventions, that are often tacit, undocumented, and difficult to elicit directly. We propose a problem setting for learning reusable natural-language rubrics from accumulated inline comments on artifacts such as human-written or LLM-generated drafts. Our method infers rubrics from these comments and iteratively refines them by observing comment-wise mismatches between rubric-conditioned predictions and reference comments. We evaluate the proposed method in real-world review settings and in controlled settings with reference rubrics. These results show that inline comments can be distilled into reusable rubrics that support comment prediction, rubric understanding, and automatic artifact revision.