ManySpace
English Giriş yap Kayıt ol

Yapay ZekâÖnerilenAIML-RSP-006

Hallucination

Ungrounded generation: detection, measurement, and mitigation that actually helps.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
3 / 5
Önem
4 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can test a claim for grounding and rank mitigations by evidence.

Bu konuya giden rota

Rota AIML-RSP-006
What Is a Model? Tasks: Regression, Classification, and Beyond Features and Targets Probabilistic Prediction Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Scores and Logits Loss and Fitting: Squared Error Similarity in Vector Space Multiclass Scores and Softmax Autoregression Objective Functions and Empirical Risk Metric Spaces and Distance Query, Key, Value Semantic Embeddings Gradient Descent in Machine Learning Likelihood Next-Token Prediction Similarity Scores Similarity Search Chunking Stochastic and Mini-batch Optimization Cross-Entropy Loss Temperature Weighted Aggregation Greedy Decoding Retrieval The Language-Modeling Objective Top-k and Top-p Sampling Self-Attention Pretraining Context and Conditioning Repetition and Structure LLM Failure Modes Retrieval-Augmented Generation Grounding and Citation Hallucination