UPCS: Unbiased Persona Construction for Dialogue Generation
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
18 of 50 references.
References · 18
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
- 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
- 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 240
- 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 179
- 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
- 2019A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Datacited by 74
- 2019Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Functioncited by 57
- 2018On the cost of essentially fair clusteringscited by 44
- 2023Large Language Models can be Guided to Evade AI-Generated Text Detectioncited by 44
- 2023Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systemscited by 37
- 2024KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completioncited by 36
6 more
- 2023PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narrativescited by 19
- 2020Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognitioncited by 11
- 2023Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descendcited by 9
- 2024Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domaincited by 2
- 2022Machine learning approach in the development of building occupant personascited by 1
- 2023Fair k-Center: a Coreset Approach in Low Dimensionscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.