# Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences

arXiv: https://arxiv.org/abs/2506.00195 · HTML: https://mlsanity.com/paper/2506.00195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Quantile Regression for Distributional Reward Models in RLHF](https://mlsanity.com/paper/2409.10164/) (2024)
- [FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning](https://mlsanity.com/paper/2505.08054/) (2025)
- [Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts](https://mlsanity.com/paper/2108.11830/) (2021)
- [When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset](https://mlsanity.com/paper/2306.06826/) (2023)
- [Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems](https://mlsanity.com/paper/2105.03748/) (2021)
- [Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions](https://mlsanity.com/paper/2308.02312/) (2023)
- [Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism](https://mlsanity.com/paper/2311.01041/) (2023)
- [Understanding Users' Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level](https://mlsanity.com/paper/2311.07434/) (2023)
- [Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making](https://mlsanity.com/paper/2209.11812/) (2022)
- [Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance](https://mlsanity.com/paper/2407.07950/) (2024)
- [Using ChatGPT in HCI Research -- A Trioethnography](https://mlsanity.com/paper/2309.12583/) (2023)

## Built on by (most cited first, 1 of 1)

- [Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations](https://mlsanity.com/paper/2604.27093/) (2026)

## Abstract (arXiv)

Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience. Through a study of 480 participants evaluating 3,840 query-response pairs, we examine how different refusal strategies affect user perceptions across varying motivations. Our findings reveal that response strategy largely shapes user experience, while actual user motivation has negligible impact. Partial compliance -- providing general information without actionable details -- emerges as the optimal strategy, reducing negative user perceptions by over 50% to flat-out refusals. Complementing this, we analyze response patterns of 9 state-of-the-art LLMs and evaluate how 6 reward models score different refusal strategies, demonstrating that models rarely deploy partial compliance naturally and reward models currently undervalue it. This work demonstrates that effective guardrails require focusing on crafting thoughtful refusals rather than detecting intent, offering a path toward AI safety mechanisms that ensure both safety and sustained user engagement.