# LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena

arXiv: https://arxiv.org/abs/2501.03266 · HTML: https://mlsanity.com/paper/2501.03266/

## Key facts

- Cited by 6 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 44 of its 104 references that are in the map.
- First posted on arXiv 4 Jan 2025.

## 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 44)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations](https://mlsanity.com/paper/2405.18392/) (2024)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties](https://mlsanity.com/paper/2309.00779/) (2023)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- ['It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions](https://mlsanity.com/paper/1801.10408/) (2018)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Don't Say No: Jailbreaking LLM by Suppressing Refusal](https://mlsanity.com/paper/2404.16369/) (2024)
- [Comparing BERT against traditional machine learning text classification](https://mlsanity.com/paper/2005.13012/) (2020)
- [Understanding User Experience in Large Language Model Interactions](https://mlsanity.com/paper/2401.08329/) (2024)

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

- [MMPB: It's Time for Multi-Modal Personalization](https://mlsanity.com/paper/2509.22820/) (2025)
- [Human-AI Interaction and User Satisfaction: Empirical Evidence from Online Reviews of AI Products](https://mlsanity.com/paper/2503.17955/) (2025)
- [Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback](https://mlsanity.com/paper/2508.08486/) (2025)
- [Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts](https://mlsanity.com/paper/2604.02713/) (2026)
- [Beyond Compliance: How AI Could Help Creative Writers by Refusing Them](https://mlsanity.com/paper/2605.16272/) (2026)
- [DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots](https://mlsanity.com/paper/2608.05004/) (2026)

## Abstract (arXiv)

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. In particular, little is known about how users respond when models refuse to answer a prompt-one of the primary mechanisms used to enforce ethical boundaries in LLMs. We address this gap by analyzing nearly 50,000 model comparisons from Chatbot Arena, a platform where users indicate their preferred LLM response in pairwise matchups, providing a large-scale setting for studying real-world user preferences. Using a novel RoBERTa-based refusal classifier fine-tuned on a hand-labeled dataset, we distinguish between refusals due to ethical concerns and technical limitations. Our results reveal a substantial refusal penalty: ethical refusals yield significantly lower win rates than both technical refusals and standard responses, indicating that users are especially dissatisfied when models decline a task for ethical reasons. However, this penalty is not uniform. Refusals receive more favorable evaluations when the underlying prompt is highly sensitive (e.g., involving illegal content), and when the refusal is phrased in a detailed and contextually aligned manner. These findings underscore a core tension in LLM design: safety-aligned behaviors may conflict with user expectations, calling for more adaptive moderation strategies that account for context and presentation.