← Search

Jens Grossklags

2 accepted papers

2025

More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation

NeurIPS 2025poster

Large language models (LLMs) have demonstrated remarkable progress in generating functional code, leading to numerous AI-based coding program tools. However, their reliance on the perplexity objective during both training and inference primarily emphasizes functionality, often at the expense of effi…

Cited by 0SourceScholar
2024

PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques

NeurIPS 2024spotlight

Large Language Models (LLMs) are recognized for their potential to be an important building block toward achieving artificial general intelligence due to their unprecedented capability for solving diverse tasks. Despite these achievements, LLMs often underperform in domain-specific tasks without tra…

Cited by 2SourcePDFScholar