Prompt Prefix
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)
Prompt Prefix has 2 facts recorded in Dontopedia across 1 reference.
2 facts·2 predicates·1 sources
Maturity scale
raw canonical shape-checked rule-derived certifiedOther facts (2)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
2 facts
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Instruction Prefix | [1] |
| Used in | Tokenization Step | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
—
typebeam/8a3d9053-ab82-4206-8ea2-43c648648492
ex:Instruction-Prefix
—
usedInbeam/8a3d9053-ab82-4206-8ea2-43c648648492
ex:tokenization-step
References (1)
1 references
ctx:claims/beam/8a3d9053-ab82-4206-8ea2-43c648648492- full textbeam-chunktext/plain1 KB
doc:beam/8a3d9053-ab82-4206-8ea2-43c648648492Show excerpt
Your current implementation uses `np.argmax(outputs.logits)` which suggests you are treating the reformulation as a classification problem. However, query reformulation is often better handled as a sequence-to-sequence task. Instead of clas…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.