arXiv:2409.05257
UPCS: Unbiased Persona Construction for Dialogue Generation
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Movie Recommendation
GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environments
When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
Subtractive Aggregation for Attributed Network Anomaly Detection
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
토론
이 논문과 연결된 포럼 글이 아직 없습니다.