Separate glossary context from prompt protection
This commit is contained in:
@@ -17,7 +17,7 @@ collections:
|
||||
- Inappropriate example: correcting "Lyra" to "Jesters" should be omitted because those words are not similar in spoken English, even if "Jesters" appears in the glossary.
|
||||
- Do not replace one clear glossary term, character name, location, or ordinary word with a different glossary term unless it is a plausible mishearing.
|
||||
- Preserve correctly identified glossary names and aliases. A recognized glossary term may still be a mishearing of another term; correct that misidentification only when spoken similarity and surrounding context support it.
|
||||
- Apart from that supported mishearing exception, do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases away from their glossary spelling.
|
||||
- Preserve spellings listed under Protected spellings. Glossary context supplies correction targets and guidance.
|
||||
- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.
|
||||
- If a segment includes categories, treat them as additional transcript context.
|
||||
- Plural forms of glossary names and aliases are allowed targets when spoken similarity and context support them, even if the plural is not explicitly listed in the glossary.
|
||||
@@ -28,9 +28,12 @@ collections:
|
||||
|
||||
{{ .HardeningPolicy }}
|
||||
|
||||
{{ .TranscriptDescriptionBlock }}Glossary:
|
||||
{{ .TranscriptDescriptionBlock }}Glossary context:
|
||||
{{ .GlossaryJSON }}
|
||||
|
||||
Protected spellings:
|
||||
{{ .ProtectedTermsJSON }}
|
||||
|
||||
Transcript section:
|
||||
{{ .SectionJSON }}
|
||||
output:
|
||||
|
||||
@@ -18,8 +18,7 @@ collections:
|
||||
- Apart from the a/an article exception, do not make word substitutions, spelling fixes, homophone fixes, filler cleanup, repetition cleanup, paraphrases, or other semantic rewrites.
|
||||
- Do not change one written word into a different written word, except for capitalization changes to the same letters and the a/an article exception.
|
||||
- If a possible correction depends on changing a content word into a different word, omit it here rather than bundling it together with formatting cleanup.
|
||||
- Treat glossary names and aliases as protected spellings and context.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases away from their glossary spelling.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter spellings listed under Protected spellings away from their glossary spelling.
|
||||
- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.
|
||||
- If a segment includes categories, treat them as additional transcript context.
|
||||
- Choose an original_text span that appears exactly once in the current segment text.
|
||||
@@ -31,9 +30,12 @@ collections:
|
||||
|
||||
{{ .HardeningPolicy }}
|
||||
|
||||
{{ .TranscriptDescriptionBlock }}Protected glossary/context:
|
||||
{{ .TranscriptDescriptionBlock }}Glossary context:
|
||||
{{ .GlossaryJSON }}
|
||||
|
||||
Protected spellings:
|
||||
{{ .ProtectedTermsJSON }}
|
||||
|
||||
Transcript section:
|
||||
{{ .SectionJSON }}
|
||||
output:
|
||||
|
||||
@@ -16,9 +16,8 @@ collections:
|
||||
- Reject unrelated substitutions like changing "Lyra" to "Jesters".
|
||||
- Reject antonyms or reversals such as changing "visible" to "invisible".
|
||||
- Do not add or remove punctuation, alter capitalization only, normalize spacing, remove filler words, collapse repetitions, or make general readability edits.
|
||||
- Treat glossary names and aliases as protected spellings and context.
|
||||
- You may correct toward glossary names, aliases, or their plural forms when the correction is acoustically plausible and supported by local context.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases that already appear correctly in the transcript.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter spellings listed under Protected spellings that already appear correctly in the transcript.
|
||||
- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.
|
||||
- If a segment includes categories, treat them as additional transcript context.
|
||||
- Choose an original_text span that appears exactly once in the current segment text.
|
||||
@@ -28,9 +27,12 @@ collections:
|
||||
|
||||
{{ .HardeningPolicy }}
|
||||
|
||||
{{ .TranscriptDescriptionBlock }}Protected glossary/context:
|
||||
{{ .TranscriptDescriptionBlock }}Glossary context:
|
||||
{{ .GlossaryJSON }}
|
||||
|
||||
Protected spellings:
|
||||
{{ .ProtectedTermsJSON }}
|
||||
|
||||
Transcript section:
|
||||
{{ .SectionJSON }}
|
||||
output:
|
||||
|
||||
@@ -20,8 +20,8 @@ collections:
|
||||
- Do not paraphrase, summarize, reorder ideas, replace content with different wording, or make substantive semantic edits.
|
||||
- Do not change clear content words just because a different phrasing reads better.
|
||||
- Do not convert uncertain statements into certain statements.
|
||||
- Treat glossary names and aliases as protected spellings and context. Accidental repetition of a protected name may be reduced when that identity remains in the segment; preserve substantive references and intentional emphasis.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases that already appear correctly in the transcript.
|
||||
- Accidental repetition of a protected name may be reduced when that identity remains in the segment; preserve substantive references and intentional emphasis.
|
||||
- Do not replace, Anglicize, normalize, lowercase, or otherwise alter spellings listed under Protected spellings that already appear correctly in the transcript.
|
||||
- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.
|
||||
- If a segment includes categories, treat them as additional transcript context.
|
||||
- Choose an original_text span that appears exactly once in the current segment text.
|
||||
@@ -33,9 +33,12 @@ collections:
|
||||
|
||||
{{ .HardeningPolicy }}
|
||||
|
||||
{{ .TranscriptDescriptionBlock }}Protected glossary/context:
|
||||
{{ .TranscriptDescriptionBlock }}Glossary context:
|
||||
{{ .GlossaryJSON }}
|
||||
|
||||
Protected spellings:
|
||||
{{ .ProtectedTermsJSON }}
|
||||
|
||||
Transcript section:
|
||||
{{ .SectionJSON }}
|
||||
output:
|
||||
|
||||
@@ -93,6 +93,9 @@ func WithSharedVariables(values map[string]string) map[string]string {
|
||||
result[key] = value
|
||||
}
|
||||
}
|
||||
if _, exists := result["ProtectedTermsJSON"]; !exists {
|
||||
result["ProtectedTermsJSON"] = "[]"
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
|
||||
@@ -38,9 +38,7 @@ func TestEmbeddedDefinitionsPrepareThroughPromptKit(t *testing.T) {
|
||||
"SectionJSON": "{\"text\":\"fixture-section\"}",
|
||||
"PayloadJSON": "[{\"text\":\"fixture-correction\"}]",
|
||||
}
|
||||
for key, value := range SharedVariables() {
|
||||
vars[key] = value
|
||||
}
|
||||
vars = WithSharedVariables(vars)
|
||||
for _, tc := range []struct{ id, instruction, schema, payload string }{
|
||||
{PromptIDModuleGlossaryProposal, "strongly supported by the glossary", "correction_set.v1.json", "fixture-section"},
|
||||
{PromptIDModuleHomophonesProposal, "homophone correction assistant", "correction_set.v1.json", "fixture-section"},
|
||||
|
||||
Reference in New Issue
Block a user