# Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

arXiv: https://arxiv.org/abs/2407.15366 · HTML: https://mlsanity.com/paper/2407.15366/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 110 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 30 of 67)

- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)

## Built on by (most cited first, 17 of 17)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Understanding the Dark Side of LLMs' Intrinsic Self-Correction](https://mlsanity.com/paper/2412.14959/) (2024)
- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents](https://mlsanity.com/paper/2502.11355/) (2025)
- [Course-Correction: Safety Alignment Using Synthetic Preferences](https://mlsanity.com/paper/2407.16637/) (2024)
- [DebateQA: Evaluating Question Answering on Debatable Knowledge](https://mlsanity.com/paper/2408.01419/) (2024)
- [Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings](https://mlsanity.com/paper/2505.24341/) (2025)
- [Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://mlsanity.com/paper/2503.01539/) (2025)
- [AI Awareness](https://mlsanity.com/paper/2504.20084/) (2025)
- [DiPT: Enhancing LLM reasoning through diversified perspective-taking](https://mlsanity.com/paper/2409.06241/) (2024)
- [Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites](https://mlsanity.com/paper/2505.15297/) (2025)
- [Something Just Like TRuST : Toxicity Recognition of Span and Target](https://mlsanity.com/paper/2506.02326/) (2025)
- [REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting](https://mlsanity.com/paper/2509.15723/) (2025)
- [The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems](https://mlsanity.com/paper/2510.10943/) (2025)
- [DeFrame: Debiasing Large Language Models Against Framing Effects](https://mlsanity.com/paper/2602.04306/) (2026)
- [Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling](https://mlsanity.com/paper/2601.02337/) (2026)
- [Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions](https://mlsanity.com/paper/2609.40124/) (2026)

## Abstract (arXiv)

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical for cutting-edge commercial LLMs. Moreover, prevailing prompting methods depend on external tool feedback and fail to simultaneously lessen toxicity and bias. Motivated by social psychology principles, we propose a novel strategy named textbfperspective-taking prompting (textscPeT) that inspires LLMs to integrate diverse human perspectives and self-regulate their responses. This self-correction mechanism can significantly diminish toxicity (up to 89%) and bias (up to 73%) in LLMs' responses. Rigorous evaluations and ablation studies are conducted on two commercial LLMs (ChatGPT and GLM) and three open-source LLMs, revealing textscPeT's superiority in producing less harmful responses, outperforming five strong baselines.