# Using In-Context Learning to Improve Dialogue Safety

arXiv: https://arxiv.org/abs/2302.00871 · HTML: https://mlsanity.com/paper/2302.00871/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 91 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [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)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (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)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)

## Built on by (most cited first, 30 of 42)

- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [In-Context Learning with Iterative Demonstration Selection](https://mlsanity.com/paper/2310.09881/) (2023)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [AI Safety in Generative AI Large Language Models: A Survey](https://mlsanity.com/paper/2407.18369/) (2024)
- [Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning](https://mlsanity.com/paper/2310.00647/) (2023)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [High-Dimension Human Value Representation in Large Language Models](https://mlsanity.com/paper/2404.07900/) (2024)
- [Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety](https://mlsanity.com/paper/2312.06798/) (2023)
- [Fine-tune Language Models to Approximate Unbiased In-context Learning](https://mlsanity.com/paper/2310.03331/) (2023)
- [Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies](https://mlsanity.com/paper/2312.01509/) (2023)
- [Potential and Challenges of Model Editing for Social Debiasing](https://mlsanity.com/paper/2402.13462/) (2024)
- [Learn What NOT to Learn: Towards Generative Safety in Chatbots](https://mlsanity.com/paper/2304.11220/) (2023)
- [PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning](https://mlsanity.com/paper/2305.11508/) (2023)
- [Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue](https://mlsanity.com/paper/2406.06399/) (2024)
- [SAIL: Sample-Centric In-Context Learning for Document Information Extraction](https://mlsanity.com/paper/2412.17092/) (2024)
- [BiasFilter: An Inference-Time Debiasing Framework for Large Language Models](https://mlsanity.com/paper/2505.23829/) (2025)
- [TalkDep: Clinically Grounded LLM Personas for Conversation-Centric Depression Screening](https://mlsanity.com/paper/2508.04248/) (2025)
- [JAB: Joint Adversarial Prompting and Belief Augmentation](https://mlsanity.com/paper/2311.09473/) (2023)
- [Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning](https://mlsanity.com/paper/2312.17055/) (2023)
- [Investigating Adversarial Trigger Transfer in Large Language Models](https://mlsanity.com/paper/2404.16020/) (2024)
- [Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing](https://mlsanity.com/paper/2505.22298/) (2025)
- [Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems](https://mlsanity.com/paper/2405.15585/) (2024)
- [On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments](https://mlsanity.com/paper/2407.08067/) (2024)
- [Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study](https://mlsanity.com/paper/2503.15579/) (2025)

## Abstract (arXiv)

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which often perpetuates social biases or stereotypes. We investigate a retrieval-based method for reducing bias and toxicity in responses from chatbots. It uses in-context learning to steer a model towards safer generations. Concretely, to generate a response to an unsafe dialogue context, we retrieve demonstrations of safe responses to similar dialogue contexts. We find our method performs competitively with strong baselines without requiring training. For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4.04% more than our approach. Finally, we also propose a re-ranking procedure which can further improve response safeness.