All software
Inseq
Interpretability for sequence generation models 🐛 🔍
- deep learning
- Explainable AI
- generative models
- + 2
- (Dockerfile)
- (Makefile)
- (Python)
CHI2025_Plan-then-Execute_LLMAgent
User Interaction Dataset for CHI 2025 paper "Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant."
- Daily Assistant
- Human-AI Collaboration
- large language models
- + 2
- (CSS)
- (HTML)
- (JavaScript)
- + 7
thesis-code-mia-mkp
Code supporting the BSc thesis: "The Illusion of Ability: The Poisoned Promise of LLM Performance. An Evaluation of the Min-K% Prob membership inference attack."
- large language models
- Machine learning
- membership inference
- + 2
- (HTML)
- (JSON)
- (large-text-file)
- + 4
The Cultural Heritage AI Cookbook: Notebooks
Google Colab notebook that uses large language models for analyzing and expanding text metadata related to cultural heritage
- cultural heritage
- large language models
- named entity linking
- + 2
- ("Jupyter Notebook")
- (Python)
Enriching Digital Heritage (pre-workshop)
Software related to the startup phase of the project Enriching Digital Heritage
- cultural heritage
- large language models
- named entity linking
- + 1
- (Python)
Harmony
Making harmonisation simple. Social scientists often have to compare items from different questionnaires or datasets. Harmony is a tool that uses natural language processing and generative AI models to help researchers harmonise questionnaire items quickly, even in different languages.
- AI
- Data
- Data Science
- + 10
- ("Jupyter Notebook")
- (Python)