Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data

Documenti analoghi

• Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
  di: Haider, Batool, et al.
  Pubblicazione: (2025)
• Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
  di: Aggarwal, Yash, et al.
  Pubblicazione: (2026)
• Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context
  di: Das, Nilanjana, et al.
  Pubblicazione: (2024)
• COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models
  di: Govil, Priyanshul, et al.
  Pubblicazione: (2024)
• Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
  di: Chowdhury, Arijit Ghosh, et al.
  Pubblicazione: (2023)