Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
Anzeige
Ähnliche Artikel
arXiv – cs.AI
•
LLMSHAP: Prinzipielle Erklärbarkeit von Sprachmodellen mit Shapley‑Werten
arXiv – cs.AI
•
Detecting Prefix Bias in LLM-based Reward Models
arXiv – cs.AI
•
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
arXiv – cs.LG
•
Semantisch bewusste Logit‑Interventionen senken Bias in LLMs drastisch
arXiv – cs.AI
•
Safe and Efficient In-Context Learning via Risk Control
arXiv – cs.LG
•
KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning