cifkao/context-probing
Black-box language model explanation by context length probing
This tool helps AI researchers and practitioners understand how much different parts of a sentence contribute to a language model's predictions. You input a pre-trained language model and a piece of text, and it outputs visual charts showing the importance of each word's context for predicting subsequent words. It's designed for those evaluating and explaining large language models.
No commits in the last 6 months.
Use this if you need to visualize and quantify which specific words or phrases in a given context are most crucial for a language model to predict a target word.
Not ideal if you are looking for a general-purpose language model or a tool for generating text, as this focuses on model interpretability rather than direct application.
Stars
9
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/cifkao/context-probing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.