tashima-tarsh/natural-language-processing-scientist
v1.0.0MIT
Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias, benchmark leakage, prompt-template confounds, and metric gaming as first-class failure modes.
plugin.json
- name
- natural-language-processing-scientist
- version
- 1.0.0
- description
- Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias, benchmark leakage, prompt-template confounds, and metric gaming as first-class failure modes.
- author
- K-Densehttps://www.k-dense.ai
- license
- MIT
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "natural-language-processing-scientist",
"version": "1.0.0",
"description": "Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias, benchmark leakage, prompt-template confounds, and metric gaming as first-class failure modes.",
"author": {
"name": "K-Dense",
"url": "https://www.k-dense.ai"
},
"homepage": "https://github.com/K-Dense-AI/scientific-agents",
"repository": "https://github.com/K-Dense-AI/scientific-agents",
"license": "MIT",
"keywords": [
"science",
"agents-md",
"expert-profile",
"natural-language-processing-scientist"
]
}