When would you pick an encoder-decoder model instead of decoder-only?
PICTURE THIS: AN LLM TURN
Simple meaning
Encoder-decoder models such as T5 shine at transduction: translate, summarize, or map a full input to a structured output.
WHY — Transformers instead of guessing?
Why interviewers care about Transformers:
on Transformers.
the situation, the default choice, and one exception - that reads as experience.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Encoder-decoder models such as
T5 shine at transduction: translate, summarize, or map a full input to a structured output.
- 2Token IDs
Decoder-only models dominate open-ended chat.
- 3For RAG, either can
work, but ops and tooling today favor decoder-only LLMs.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
Encoder-decoder models such as T5 shine at transduction: translate, summarize, or map a full input to a structured output. Decoder-only models dominate open-ended chat.