DFKI-NLP/LLMCheckup
Code for the NAACL 2024 HCI+NLP Workshop paper "LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-explanation" (Wang et al. 2024)
This tool helps researchers and AI practitioners understand why a Large Language Model (LLM) produces a particular answer. You input an LLM's response to a prompt, and it outputs explanations using various interpretability methods, revealing the reasoning behind the LLM's output. It's designed for those who need to debug, audit, or gain insight into their LLM's behavior.
No commits in the last 6 months.
Use this if you need to analyze and explain the outputs of popular LLMs like Llama2, Mistral, or Stable Beluga 2, especially when working with text, image, or audio inputs.
Not ideal if you are looking for a pre-packaged, zero-setup solution for a specific LLM task rather than a tool for in-depth model interrogation.
Stars
13
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/DFKI-NLP/LLMCheckup"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/langfun
OO for LLMs
tanaos/artifex
Small Language Model Inference, Fine-Tuning and Observability. No GPU, no labeled data needed.
preligens-lab/textnoisr
Adding random noise to a text dataset, and controlling very accurately the quality of the result
vulnerability-lookup/VulnTrain
A tool to generate datasets and models based on vulnerabilities descriptions from @Vulnerability-Lookup.
masakhane-io/masakhane-mt
Machine Translation for Africa