# Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements

arXiv: https://arxiv.org/abs/2302.09270 · HTML: https://mlsanity.com/paper/2302.09270/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 109 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Builds on (most cited first, 30 of 64)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [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)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)

## Built on by (most cited first, 14 of 14)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [Safety Assessment of Chinese Large Language Models](https://mlsanity.com/paper/2304.10436/) (2023)
- [Beyond the Safeguards: Exploring the Security Risks of ChatGPT](https://mlsanity.com/paper/2305.08005/) (2023)
- [MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations](https://mlsanity.com/paper/2405.16584/) (2024)
- [A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models](https://mlsanity.com/paper/2311.11415/) (2023)
- ["Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process](https://mlsanity.com/paper/2305.02626/) (2023)
- [AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models](https://mlsanity.com/paper/2406.16714/) (2024)
- [Building a Domain-specific Guardrail Model in Production](https://mlsanity.com/paper/2408.01452/) (2024)
- [REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM](https://mlsanity.com/paper/2505.04673/) (2025)
- [Goal Hijacking Attack on Large Language Models via Pseudo-Conversation Injection](https://mlsanity.com/paper/2410.23678/) (2024)
- [Are Bias Evaluation Methods Biased ?](https://mlsanity.com/paper/2506.17111/) (2025)
- [COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models](https://mlsanity.com/paper/2402.14889/) (2024)
- [The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems](https://mlsanity.com/paper/2607.19292/) (2026)

## Abstract (arXiv)

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated safety risks. This survey presents a framework for safety research pertaining to large models, delineating the landscape of safety risks as well as safety evaluation and improvement methods. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models, encompassing preference-based testing, adversarial attack approaches, issues detection, and other advanced evaluation methods. Additionally, we explore the strategies for enhancing large model safety from training to deployment, highlighting cutting-edge safety approaches for each stage in building large models. Finally, we discuss the core challenges in advancing towards more responsible AI, including the interpretability of safety mechanisms, ongoing safety issues, and robustness against malicious attacks. Through this survey, we aim to provide clear technical guidance for safety researchers and encourage further study on the safety of large models.