🏠 Home
Prestatietests
📊 Alle benchmarks 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List applicaties 🎨 Creatieve vrije pagina's 🎯 FSACB - Ultieme showcase 🌍 Vertaalbenchmark
Modellen
🏆 Top 10 modellen 🆓 Gratis modellen 📋 Alle modellen ⚙️ Kilo Code
Bronnen
💬 Promptbibliotheek 📖 AI-woordenlijst 🔗 Nuttige links

AI-woordenlijst

Het complete woordenboek van kunstmatige intelligentie

162
categorieën
2.032
subcategorieën
23.060
termen
📖
termen

Constitutional AI

Alignment methodology where models follow a predefined set of principles or constitution, allowing them to self-evaluate and correct their responses according to these ethical rules.

📖
termen

Red Teaming

Systematic process of evaluating model vulnerabilities by experts actively seeking to provoke undesirable or dangerous behaviors to identify and correct weaknesses.

📖
termen

Safety Alignment

Set of techniques aimed at ensuring language models avoid generating harmful, dangerous, or inappropriate content while maintaining their overall performance.

📖
termen

Value Alignment

Process aimed at aligning the objectives and behaviors of AI systems with fundamental human values, requiring a nuanced understanding of human preferences and ethics.

📖
termen

Model Jailbreaking

Attack techniques designed to bypass model safety and alignment mechanisms, forcing them to generate normally restricted or prohibited content.

📖
termen

Reward Modeling

Approach where a reward model learns to predict human preferences, serving as a guide for reinforcement learning of main language models.

📖
termen

Constitutional Principles

Set of explicitly defined fundamental rules and principles that guide AI model behavior, ensuring consistency and alignment with desired values.

📖
termen

Preference Learning

Machine learning domain where models learn from comparisons between different options to capture human preferences and align with them.

📖
termen

Harmlessness Training

Specific training process aimed at teaching models to avoid generating potentially harmful, dangerous, or prejudicial content for users.

📖
termen

Truthfulness Alignment

Alignment objective aimed at ensuring models provide factually correct information and avoid hallucinations or unverified claims.

📖
termen

Bias Mitigation

Set of techniques to identify, quantify, and reduce systemic biases in language models, ensuring fair and non-discriminatory representation.

📖
termen

Guardrails

Safety mechanisms implemented in AI systems to monitor and filter inputs/outputs, preventing dangerous or inappropriate interactions in real-time.

📖
termen

Constitutional Supervision

Supervision method where models are guided by an explicit constitution, allowing them to self-criticize and improve their responses according to these guiding principles.

📖
termen

Human Preference Data

Dataset collected from comparative human evaluations between different model responses, serving as a basis for alignment training and optimization.

📖
termen

Safety Fine-tuning

Specific refinement phase after initial pre-training, aimed at finely adjusting model behaviors to comply with safety and ethical constraints.

📖
termen

Alignment Taxonomy

Structured classification of different types and dimensions of alignment in AI, including value alignment, safety, robustness, and model interpretability.

🔍

Geen resultaten gevonden