# Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement

arXiv: https://arxiv.org/abs/2502.06207 · HTML: https://mlsanity.com/paper/2502.06207/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://mlsanity.com/paper/1908.06083/) (2019)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement](https://mlsanity.com/paper/2109.13563/) (2021)
- [SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)](https://mlsanity.com/paper/2304.14803/) (2023)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [Evaluating GPT-3 Generated Explanations for Hateful Content Moderation](https://mlsanity.com/paper/2305.17680/) (2023)
- [You Are What You Annotate: Towards Better Models through Annotator Representations](https://mlsanity.com/paper/2305.14663/) (2023)
- [Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets](https://mlsanity.com/paper/2410.07991/) (2024)
- [Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks](https://mlsanity.com/paper/2311.09743/) (2023)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection](https://mlsanity.com/paper/2402.11406/) (2024)
- [Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security](https://mlsanity.com/paper/2404.05264/) (2024)

## Built on by (most cited first, 14 of 14)

- [Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage](https://mlsanity.com/paper/2601.01685/) (2026)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [CoPE: A Small Language Model for Steerable and Scalable Content Labeling](https://mlsanity.com/paper/2512.18027/) (2025)
- [Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks](https://mlsanity.com/paper/2603.05801/) (2026)
- [RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems](https://mlsanity.com/paper/2601.02917/) (2026)
- [Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis](https://mlsanity.com/paper/2605.10415/) (2026)
- [SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs](https://mlsanity.com/paper/2606.05376/) (2026)
- [Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification](https://mlsanity.com/paper/2601.08668/) (2026)
- [Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations](https://mlsanity.com/paper/2605.27025/) (2026)
- [HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations](https://mlsanity.com/paper/2601.13547/) (2026)
- [GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules](https://mlsanity.com/paper/2603.01724/) (2026)
- [Task Decomposition for Efficient Annotation](https://mlsanity.com/paper/2606.24734/) (2026)
- [Toward Interactive Understanding of Code APIs](https://mlsanity.com/paper/2609.32081/) (2026)
- [Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages](https://mlsanity.com/paper/2610.18588/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have become essential for offensive language detection, yet their ability to handle annotation disagreement remains underexplored. Disagreement samples, which arise from subjective interpretations, pose a unique challenge due to their ambiguous nature. Understanding how LLMs process these cases, particularly their confidence levels, can offer insight into their alignment with human annotators. This study systematically evaluates the performance of multiple LLMs in detecting offensive language at varying levels of annotation agreement. We analyze binary classification accuracy, examine the relationship between model confidence and human disagreement, and explore how disagreement samples influence model decision-making during few-shot learning and instruction fine-tuning. Our findings reveal that LLMs struggle with low-agreement samples, often exhibiting overconfidence in these ambiguous cases. However, utilizing disagreement samples in training improves both detection accuracy and model alignment with human judgment. These insights provide a foundation for enhancing LLM-based offensive language detection in real-world moderation tasks.