# REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations

arXiv: https://arxiv.org/abs/2604.17289 · HTML: https://mlsanity.com/paper/2604.17289/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation](https://mlsanity.com/paper/2211.02570/) (2022)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach](https://mlsanity.com/paper/2010.07835/) (2020)
- [RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge](https://mlsanity.com/paper/2101.00376/) (2021)
- [Imitation Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2202.01288/) (2022)
- [Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality](https://mlsanity.com/paper/2110.14754/) (2021)
- [TRAIL: Near-Optimal Imitation Learning with Suboptimal Data](https://mlsanity.com/paper/2110.14770/) (2021)
- [Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance](https://mlsanity.com/paper/2311.01108/) (2023)
- [RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response](https://mlsanity.com/paper/2412.14922/) (2024)
- [Decentralized Low-Rank Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2501.15361/) (2025)
- [Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.13097/) (2024)
- [Inverse Reinforcement Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2402.01886/) (2024)
- [Robust Decentralized Learning with Local Updates and Gradient Tracking](https://mlsanity.com/paper/2405.00965/) (2024)

## Built on by (most cited first, 1 of 1)

- [Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility](https://mlsanity.com/paper/2608.04001/) (2026)

## Abstract (arXiv)

Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise. Standard practice aggregates labels via majority vote or simple averaging, discarding annotator identity and causing the model to absorb the errors of unreliable annotators into its parameters. We propose REALM, which jointly learns the model parameters and a scalar expertise value for each annotator, entirely unsupervised and requiring nothing beyond annotator identity. The key idea is to model each observed label as a mixture between the model's prediction and a uniform random guess, weighted by the annotator's learned expertise. REALM applies to any task with a fixed label set, and extends to multiple tasks via a learned expertise matrix. On four text-classification datasets with real crowdsourced annotations, REALM is the best method in all 12 configurations of the three heterogeneous-annotator datasets, improving on the strongest applicable baseline, including majority vote and Dawid--Skene aggregation, by +2.9 points on average. On five question answering benchmarks with simulated noisy labels, it outperforms naive noisy fine-tuning in 152 of 162 configurations, by +5.0 points on average, with gains that grow with model capacity. The learned expertise additionally recovers annotator reliability without ever observing it. Our code is available at https://github.com/sajjad-ucsb/REALM