# GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives

arXiv: https://arxiv.org/abs/2311.05074 · HTML: https://mlsanity.com/paper/2311.05074/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 33 of its 85 references that are in the map.
- First posted on arXiv 9 Nov 2023.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [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)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [On Releasing Annotator-Level Labels and Information in Datasets](https://mlsanity.com/paper/2110.05699/) (2021)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Designing Toxic Content Classification for a Diversity of Perspectives](https://mlsanity.com/paper/2106.04511/) (2021)
- [Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation](https://mlsanity.com/paper/2112.04554/) (2021)
- [When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset](https://mlsanity.com/paper/2306.06826/) (2023)
- [The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics](https://mlsanity.com/paper/2306.11559/) (2023)
- [You Are What You Annotate: Towards Better Models through Annotator Representations](https://mlsanity.com/paper/2305.14663/) (2023)
- [Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots](https://mlsanity.com/paper/2209.03463/) (2022)
- [Cross-replication Reliability -- An Empirical Approach to Interpreting Inter-rater Reliability](https://mlsanity.com/paper/2106.07393/) (2021)
- [Detecting Unintended Social Bias in Toxic Language Datasets](https://mlsanity.com/paper/2210.11762/) (2022)
- [Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets](https://mlsanity.com/paper/2112.03529/) (2021)
- [Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers](https://mlsanity.com/paper/2210.07362/) (2022)

## Built on by (most cited first, 16 of 16)

- [A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models](https://mlsanity.com/paper/2403.12025/) (2024)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [Value Profiles for Encoding Human Variation](https://mlsanity.com/paper/2503.15484/) (2025)
- [Annotation alignment: Comparing LLM and human annotations of conversational safety](https://mlsanity.com/paper/2406.06369/) (2024)
- [Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models](https://mlsanity.com/paper/2507.13383/) (2025)
- ["Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People](https://mlsanity.com/paper/2410.03448/) (2024)
- [Natural Language Processing RELIES on Linguistics](https://mlsanity.com/paper/2405.05966/) (2024)
- [Rater Cohesion and Quality from a Vicarious Perspective](https://mlsanity.com/paper/2408.08411/) (2024)
- [Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups](https://mlsanity.com/paper/2410.17032/) (2024)
- [Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech](https://mlsanity.com/paper/2502.09004/) (2025)
- [A Unified Framework to Quantify Cultural Intelligence of AI](https://mlsanity.com/paper/2603.01211/) (2026)
- [Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection](https://mlsanity.com/paper/2512.09662/) (2025)
- [Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions](https://mlsanity.com/paper/2509.08217/) (2025)
- [Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM](https://mlsanity.com/paper/2604.08425/) (2026)
- [Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment](https://mlsanity.com/paper/2608.30842/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Human annotation plays a core role in machine learning -- annotations for supervised models, safety guardrails for generative models, and human feedback for reinforcement learning, to cite a few avenues. However, the fact that many of these human annotations are inherently subjective is often overlooked. Recent work has demonstrated that ignoring rater subjectivity (typically resulting in rater disagreement) is problematic within specific tasks and for specific subgroups. Generalizable methods to harness rater disagreement and thus understand the socio-cultural leanings of subjective tasks remain elusive. In this paper, we propose GRASP, a comprehensive disagreement analysis framework to measure group association in perspectives among different rater sub-groups, and demonstrate its utility in assessing the extent of systematic disagreements in two datasets: (1) safety annotations of human-chatbot conversations, and (2) offensiveness annotations of social media posts, both annotated by diverse rater pools across different socio-demographic axes. Our framework (based on disagreement metrics) reveals specific rater groups that have significantly different perspectives than others on certain tasks, and helps identify demographic axes that are crucial to consider in specific task contexts.