Tag
length-normalization
- Jan 24, 2024 Beam Search Decoding: Scoring, Length Normalization, and Pruning How a decoder searches over sequences instead of choosing per step, why accumulated log-probabilities need a length term, and how beam width trades compute for coverage. deep learning
- Jul 25, 2022 BM25 Term Saturation and Document Length Normalization How the BM25 scoring function bounds the reward for repeated query terms, what the k1 and b parameters actually control, and where the model breaks down. information retrieval