token-level-analysis

Here are 2 public repositories matching this topic...

Chi-Shan0707 / code-not-text

Cross-domain limits of hand-crafted CoT-surface features: AUROC 0.982 in math, 0.434 in coding. Five methods, one conclusion—code correctness is not in the text.

science verify demo math code prediction cot llm token-level-analysis neuron-activation

Updated May 19, 2026
Python

llm-lab-org / MENA-Values-Benchmark-Evaluating-Cultural-Alignment-and-Multilingual-Bias-in-Large-Language-Models

Star

This repository contains the dataset and code used in our paper, “I Am Aligned, But With Whom? Diagnosing Structural Alignment Failures in Multilingual LLMs” It provides tools to evaluate how LLMs represent cultural values across 16 countries, multiple languages, and perspectives.

ai-alignment ai-fairness multilingual-nlp nlp-evaluation cultural-ai mena-region token-level-analysis

Updated Mar 3, 2026
HTML

Add this topic to your repo

To associate your repository with the token-level-analysis topic, visit your repo's landing page and select "manage topics."

Learn more