# Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance

arXiv: https://arxiv.org/abs/2410.18889 · HTML: https://mlsanity.com/paper/2410.18889/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 101 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 30 of 65)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)

## Built on by (most cited first, 20 of 20)

- [The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs](https://mlsanity.com/paper/2501.10970/) (2025)
- [Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets](https://mlsanity.com/paper/2503.17502/) (2025)
- [DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality](https://mlsanity.com/paper/2603.05912/) (2026)
- [Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback](https://mlsanity.com/paper/2512.03208/) (2025)
- [BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks](https://mlsanity.com/paper/2602.06221/) (2026)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [AI Evaluation Should Require Standardized Item-Level Data Releases](https://mlsanity.com/paper/2604.03244/) (2026)
- [SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models](https://mlsanity.com/paper/2608.04975/) (2026)
- [Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness](https://mlsanity.com/paper/2505.13418/) (2025)
- [Multi-Domain Explainability of Preferences](https://mlsanity.com/paper/2505.20088/) (2025)
- [Beyond Agreement: Rethinking Ground Truth in Educational AI Annotation](https://mlsanity.com/paper/2508.00143/) (2025)
- [Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight](https://mlsanity.com/paper/2512.19691/) (2025)
- [How well do Large Language Models Recognize Instructional Moves? Establishing Baselines for Foundation Models in Educational Discourse](https://mlsanity.com/paper/2512.19903/) (2025)
- [Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale](https://mlsanity.com/paper/2603.08406/) (2026)
- [From Label Error Detection to Correction: A Modular Framework and Benchmark for Object Detection Datasets](https://mlsanity.com/paper/2508.06556/) (2025)
- [Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment](https://mlsanity.com/paper/2605.08462/) (2026)
- [Algebraic Multigrid Acceleration for Efficient Label Spreading](https://mlsanity.com/paper/2608.26309/) (2026)
- [English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck](https://mlsanity.com/paper/2609.17554/) (2026)
- [Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents](https://mlsanity.com/paper/2609.33955/) (2026)
- [It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them](https://mlsanity.com/paper/2609.37863/) (2026)

## Abstract (arXiv)

NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale well with the growing demand for larger datasets required by modern models. While crowd-sourcing provides a more scalable solution, it often comes at the expense of annotation precision and consistency. Recent advancements in large language models (LLMs) offer new opportunities to enhance the annotation process, particularly for detecting label errors in existing datasets. In this work, we consider the recent approach of LLM-as-a-judge, leveraging an ensemble of LLMs to flag potentially mislabeled examples. We conduct a case study on four factual consistency datasets from the TRUE benchmark, spanning diverse NLP tasks, and on SummEval, which uses Likert-scale ratings of summary quality across multiple dimensions. We empirically analyze the labeling quality of existing datasets and compare expert, crowd-sourced, and LLM-based annotations in terms of the agreement, label quality, and efficiency, demonstrating the strengths and limitations of each annotation method. Our findings reveal a substantial number of label errors, which, when corrected, induce a significant upward shift in reported model performance. This suggests that many of the LLMs' so-called mistakes are due to label errors rather than genuine model failures. Additionally, we discuss the implications of mislabeled data and propose methods to mitigate them in training to improve performance.