Subprober is a powerful and efficient subdomain scanning tool written in Python. With the ability to handle large lists of subdomains. The tool offers concurrent scanning, allowing users to define their preferred concurrency level for faster results. Whether you are on Linux, Windows, or macos

[NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Network probing tool crafted for datacenters (but not only)

Framework for probing tasks

The official code and dataset for EMNLP 2022 paper "COPEN: Probing Conceptual Knowledge in Pre-trained Language Models".

[NAACL 2022 Findings]Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning

Official repository for the paper: "Probing LLMs for Joint Encoding of Linguistic Categories." Findings of EMNLP 2023.

Memory efficient convolution networks

Code and data for the EMNLP 2020 paper "Intrinsic Probing through Dimension Selection".

Probing for Predicate Argument Structures in Pretrained Language Models (ACL 2022).

This repo contains a challenging dataset for sentiment analysis, as well as a python script to calculate per class results presented in at BlackboxNLP 2019

A framework for ASR probing using MDL approach

Code and data for the ACL 2022 paper "Probing as Quantifying Inductive Bias".

Repository with code for interpretability analyses of a recurrent neural network predicting German plural nouns.

Probe and cluster antibody paratopes and clonotypes

Probing Bert for part of speech (POS) and named entity recognition (NER) to alleviate the opacity of learned representations.

Causal Probing of a Bi-Encoder for Retrieval

The codebase for "DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models"

Tool to check if HTTP and HTTPS domains are resolving.