CONCEPT Cited by 1 source
Catalog-aware scoring head¶
Definition¶
A catalog-aware scoring head is a neural network output layer that constrains the model's predictions to a known, fixed catalog of items — rather than generating arbitrary tokens from a vocabulary. Each catalog item has a learned embedding eᵢ, and a scoring function combines the model's hidden representation h with these embeddings to produce per-item scores.
Mechanics¶
- The backbone LLM produces a pooled hidden state h from the input prompt.
- Each catalog item i is represented by a learned embedding vector eᵢ.
- A scoring head φ(h, eᵢ) (dot product or small MLP) produces a scalar score sᵢ.
- Softmax over all scores yields a probability distribution converted to a ranking.
All parameters — backbone, scoring head, and item embeddings — are trained jointly.
Why It Matters¶
Standard LLM outputs are token sequences from a vocabulary — they can hallucinate items that don't exist. A catalog-aware head:
- Eliminates hallucination — output is constrained to real, in-catalog items.
- Enables efficient batch scoring — single matmul h × E^T scores the full catalog.
- Supports business constraints — catalog updates (new releases, removals) are handled by updating the embedding table, not retraining the backbone.
- Compatible with sampled softmax — for very large catalogs, training uses candidate subsets.
Distinction from Autoregressive Recommendation¶
| Approach | GenPage-style (autoregressive) | GenRec-style (scoring head) |
|---|---|---|
| Output | Generated sequence of item tokens | Per-item scores via matmul |
| Decoding | Token-by-token | Single forward pass |
| Hallucination risk | Possible (constrained decoding mitigates) | Zero (scores only catalog items) |
| Business rules | Enforced via constrained decoding masks | Enforced at scoring/filtering layer |
Seen in¶
- sources/2026-07-30-netflix-genrec-towards-llm-native-recommendation — "Each catalog item i has a learned embedding eᵢ. A scoring head φ combines h and eᵢ … to produce a score sᵢ. Applying a softmax over scores yields a probability distribution which we convert into a ranking."