Tag: LLM reliability
Browse our exclusive articles!
Robust Conformal Prediction for LLMs Using Internal Data
Enhance LLM reliability with robust conformal prediction leveraging internal representations for better uncertainty quantification and cross-domain perform...
Detecting Silent Correctness Bugs in PyTorch Compiler
Explore how AlignGuard detects silent correctness bugs in PyTorch compiler, improving reliability for AI and deep learning models.
Source-Faithful Explanation Planning in Retrieval-Augmented LLMs
Enhance source-faithful explanations in retrieval-augmented language models using illocutionary planning and chain-of-illocution prompting for better relia...
Swiss-Bench 003: Assessing LLM Reliability & Security
Discover Swiss-Bench 003, a framework evaluating LLM reliability and adversarial security for Swiss financial and regulatory compliance.
Reliable Truth-Aligned Uncertainty Estimation for LLMs
Enhance large language models' reliability with Truth AnChoring, a method for accurate truth-aligned uncertainty estimation and calibration.