# UPCS: Unbiased Persona Construction for Dialogue Generation

arXiv: https://arxiv.org/abs/2409.05257 · HTML: https://mlsanity.com/paper/2409.05257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [You Impress Me: Dialogue Generation via Mutual Persona Perception](https://mlsanity.com/paper/2004.05388/) (2020)
- [A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data](https://mlsanity.com/paper/1911.04700/) (2019)
- [Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function](https://mlsanity.com/paper/1905.12801/) (2019)
- [On the cost of essentially fair clusterings](https://mlsanity.com/paper/1811.10319/) (2018)
- [Large Language Models can be Guided to Evade AI-Generated Text Detection](https://mlsanity.com/paper/2305.10847/) (2023)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion](https://mlsanity.com/paper/2402.02389/) (2024)
- [PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives](https://mlsanity.com/paper/2305.02364/) (2023)
- [Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2006.07845/) (2020)
- [Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend](https://mlsanity.com/paper/2302.02568/) (2023)
- [Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain](https://mlsanity.com/paper/2401.06742/) (2024)
- [Machine learning approach in the development of building occupant personas](https://mlsanity.com/paper/2207.11239/) (2022)
- [Fair k-Center: a Coreset Approach in Low Dimensions](https://mlsanity.com/paper/2302.09911/) (2023)

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

- [Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction](https://mlsanity.com/paper/2505.08266/) (2025)

## Abstract (arXiv)

Narrative systems, such as dialogue and storytelling systems, often utilize persona profiles to enhance personalized interactions. Existing persona profiles frequently exhibit biases, posing risks to system integrity and fairness. To address this, we introduce the UPCS framework, which categorizes character descriptions into eight dimensions, including bias mitigation strategies. Experimental results demonstrate UPCS's superiority in accuracy, diversity, bias elimination, and user satisfaction, marking a significant advancement in persona construction for reliable narrative systems.