We have 3 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large language models (LLMs) are increasingly used as classifiers, yet they operate as opaque systems whose decisions are difficult to interpret, which complicates their use in regulated domains such as credit scoring or medical diagnosis. We propose an evolutionary framework that iteratively discovers natural language...
Test-Time Augmentation is studied, finding that TTA is most cost-effective for mid-tier models where a stronger model is unavailable or too expensive, and varying the input converts inference compute into accuracy more efficiently than varying the reasoning path alone.
A striking method-dependent pattern is revealed: simple averaging degrades sharply with overfitting, while sparsification-based methods achieve their best performance well past the validation optimum, suggesting that training duration and merging method should be chosen jointly rather than independently.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
