Look before you leap: An exploratory study of uncertainty measurement for large language models
The recent performance leap of Large Language Models (LLMs) opens up new
opportunities across numerous industrial applications and domains. However, erroneous …
opportunities across numerous industrial applications and domains. However, erroneous …
[HTML][HTML] Bias and Ethics of AI Systems Applied in Auditing-A Systematic Review
The integration of artificial intelligence into auditing shows great potential in enhancing
automation and gaining insights from complex data. However, it also presents significant …
automation and gaining insights from complex data. However, it also presents significant …
Active Testing of Large Language Model via Multi-Stage Sampling
Performance evaluation plays a crucial role in the development life cycle of large language
models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and …
models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and …
Trustworthiness Assurance Assessment for High-Risk AI-Based Systems
G Stettinger, P Weissensteiner, S Khastgir - IEEE Access, 2024 - ieeexplore.ieee.org
This work proposes methodologies for ensuring the trustworthiness of high-risk artificial
intelligence (AI) systems (AIS) to achieve compliance with the European Union's (EU) AI Act …
intelligence (AI) systems (AIS) to achieve compliance with the European Union's (EU) AI Act …
Look Before You Leap: An Exploratory Study of Uncertainty Analysis for Large Language Models
The recent performance leap of Large Language Models (LLMs) opens up new
opportunities across numerous industrial applications and domains. However, the potential …
opportunities across numerous industrial applications and domains. However, the potential …
Hallucination Detection in LLMs: Using Bayesian Neural Network Ensembling
GY Arteaga - 2024 - diva-portal.org
Large language models often hallucinate, producing outputs that appear plausible but lack
factual support or deviate from given instructions. This thesis investigates methods for …
factual support or deviate from given instructions. This thesis investigates methods for …
Applications of Certainty Scoring for Machine Learning Classification and Out-of-Distribution Detection
Quantitative characterizations and estimations of uncertainty are of fundamental importance
for machine learning classification, particularly in safety-critical settings where continuous …
for machine learning classification, particularly in safety-critical settings where continuous …