Papers with judgment model

1 papers
Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective (2025.acl-long)

Copied to clipboard

Challenge: Existing code security benchmarks focus on one task and paradigm, such as code completion and generation, without comprehensive assessment across dimensions like secure code generation, vulnerability repair and discrimination.
Approach: They propose a multi-task benchmark for comprehensive evaluation of LLM code security . they also propose VC-Judge, an improved judgment model that aligns closely with human experts .
Outcome: The proposed model can evaluate LLM-generated programs for vulnerabilities in a more efficient and reliable way.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations