CodeBERT
PulseAugur coverage of CodeBERT — every cluster mentioning CodeBERT across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Open LLMs Compared to TF-IDF and CodeBERT for Bug Severity Classification
A new study published on arXiv compares the effectiveness of fine-tuned open large language models (LLMs) against traditional methods like TF-IDF and CodeBERT for classifying bug severity in Eclipse reports. The researc…
-
New C2C framework uses AI to pinpoint software bugs more accurately
Researchers have developed a new framework called C2C (From Codebase to Culprit) designed to improve the accuracy and efficiency of bug localization in software development. C2C utilizes a two-stage process that combine…
-
LangSelect optimizes LLM code generation by routing to cost-effective languages
Researchers have developed LangSelect, a novel system designed to optimize Large Language Model (LLM) code generation by intelligently routing requests to the most cost-effective target programming language. This approa…
-
New benchmarks released for LLM-based Java and Rust vulnerability detection
Two new benchmarks, JavaVulBench and RustMizan, have been released to evaluate the capabilities of large language models in detecting software vulnerabilities. JavaVulBench focuses on Java methods and includes over 1,74…
-
New SALSA method improves machine-generated code detection
Researchers have developed a new method called SALSA (Single-pass Autoregressive LLM Structured Classification) to detect machine-generated code. This approach treats code authorship detection as a binary classification…
-
New framework improves credential leak detection in code
Researchers have developed a new framework to improve the detection of credential leaks in public code repositories. This hybrid approach combines CodeBERT's semantic understanding with character-level pattern recogniti…
-
Archaeology team fine-tunes code models for AI-generated code detection
Researchers from the team Archaeology have developed a system for detecting AI-generated code, participating in SemEval-2026 Task 13. Their approach involves fine-tuning several pre-trained code models, including CodeBE…
-
Researchers develop graph construction for imperative programs using neural methods
Researchers have developed a pipeline to convert imperative programs and their annotations into typed, attributed graphs. This process combines abstract syntax tree parsing with semantic embeddings from models like Sent…