# Trust & Safety of LLMs and LLMs in Trust & Safety

arXiv: https://arxiv.org/abs/2412.02113 · HTML: https://mlsanity.com/paper/2412.02113/

## Key facts

- Cited by 3 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 16 of its 27 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## 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, 16 of 16)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection](https://mlsanity.com/paper/2401.03737/) (2024)
- [Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Healthcare Professionals](https://mlsanity.com/paper/2403.14691/) (2024)
- [On Efficient and Statistical Quality Estimation for Data Annotation](https://mlsanity.com/paper/2405.11919/) (2024)
- [Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination](https://mlsanity.com/paper/2406.13929/) (2024)
- [Evaluating Deduplication Techniques for Economic Research Paper Titles with a Focus on Semantic Similarity using NLP and LLMs](https://mlsanity.com/paper/2410.01141/) (2024)

## Built on by (most cited first, 3 of 3)

- [Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2509.16696/) (2025)
- [CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments](https://mlsanity.com/paper/2508.19932/) (2025)
- [Red Teaming for Generative AI, Report on a Copyright-Focused Exercise Completed in an Academic Medical Center](https://mlsanity.com/paper/2506.22523/) (2025)

## Abstract (arXiv)

In recent years, Large Language Models (LLMs) have garnered considerable attention for their remarkable abilities in natural language processing tasks. However, their widespread adoption has raised concerns pertaining to trust and safety. This systematic review investigates the current research landscape on trust and safety in LLMs, with a particular focus on the novel application of LLMs within the field of Trust and Safety itself. We delve into the complexities of utilizing LLMs in domains where maintaining trust and safety is paramount, offering a consolidated perspective on this emerging trend. By synthesizing findings from various studies, we identify key challenges and potential solutions, aiming to benefit researchers and practitioners seeking to understand the nuanced interplay between LLMs and Trust and Safety. This review provides insights on best practices for using LLMs in Trust and Safety, and explores emerging risks such as prompt injection and jailbreak attacks. Ultimately, this study contributes to a deeper understanding of how LLMs can be effectively and responsibly utilized to enhance trust and safety in the digital realm.