Fabbernat/Thesis
My Bachelor's Thesis: Reviewing the Consistency of Semantical Capabilities of Large Language Models. For documentation see [https://github.com/Fabbernat/Thesis-paper]
What's novel
My Bachelor's Thesis: Reviewing the Consistency of Semantical Capabilities of Large Language Models. For documentation see [https://github.com/Fabbernat/Thesis-paper]
Code Analysis
0 files read · 5 roundsA Python framework intended to evaluate Large Language Models on the Word-in-Context (WiC) benchmark using a three-stage pipeline (prompt preparation, inference, result processing), but the core implementation logic is inaccessible for review.
Strengths
The project has a well-defined structure with clear separation between data loading, model inference, and result processing modules. The README accurately describes the intended workflow and supported models.
Weaknesses
Unable to verify code quality due to inaccessible source files; no tests found in the accessible file tree; reliance on external Hugging Face libraries without visible custom logic suggests a wrapper-heavy implementation rather than novel algorithms.
Score Breakdown
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
476
Contributors
3
Files
210
Active weeks
43
Repository
Language
Python
Stars
1
Forks
0
License
—