# Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities

arXiv: https://arxiv.org/abs/2311.00203 · HTML: https://mlsanity.com/paper/2311.00203/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement](https://mlsanity.com/paper/2109.13563/) (2021)
- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation](https://mlsanity.com/paper/2206.08931/) (2022)
- ["What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness](https://mlsanity.com/paper/2011.02282/) (2020)
- [Like trainer, like bot? Inheritance of bias in algorithmic content moderation](https://mlsanity.com/paper/1707.01477/) (2017)
- [Cross-replication Reliability -- An Empirical Approach to Interpreting Inter-rater Reliability](https://mlsanity.com/paper/2106.07393/) (2021)
- [CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement](https://mlsanity.com/paper/1808.06080/) (2018)
- [Investigating the Benefits of Free-Form Rationales](https://mlsanity.com/paper/2206.11083/) (2022)
- [Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets](https://mlsanity.com/paper/2112.03529/) (2021)

## Built on by (most cited first, 6 of 6)

- [Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia](https://mlsanity.com/paper/2402.14147/) (2024)
- [Large Language Models Do Multi-Label Classification Differently](https://mlsanity.com/paper/2505.17510/) (2025)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [Re-examining Sexism and Misogyny Classification with Annotator Attitudes](https://mlsanity.com/paper/2410.03543/) (2024)
- [Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts](https://mlsanity.com/paper/2505.17222/) (2025)
- [Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors](https://mlsanity.com/paper/2410.13776/) (2024)

## Abstract (arXiv)

The prevalence and impact of toxic discussions online have made content moderation crucial.Automated systems can play a vital role in identifying toxicity, and reducing the reliance on human moderation.Nevertheless, identifying toxic comments for diverse communities continues to present challenges that are addressed in this paper.The two-part goal of this study is to(1)identify intuitive variances from annotator disagreement using quantitative analysis and (2)model the subjectivity of these viewpoints.To achieve our goal, we published a new datasetfootnoteurlhttps://github.com/XXX with expert annotators' annotations and used two other public datasets to identify the subjectivity of toxicity.Then leveraging the Large Language Model(LLM),we evaluate the model's ability to mimic diverse viewpoints on toxicity by varying size of the training data and utilizing same set of annotators as the test set used during model training and a separate set of annotators as the test set.We conclude that subjectivity is evident across all annotator groups, demonstrating the shortcomings of majority-rule voting. Moving forward, subjective annotations should serve as ground truth labels for training models for domains like toxicity in diverse communities.