Linting instruction files for seeded vocabulary
Parent: Instruction-file hygiene for LLM lexical tics: linting, mirroring, hook filtering · Published reference · snapshot 2026-09-23
↓ Facts as markdownall context files
Source-anchored research for Linting instruction files for seeded vocabulary. Run status: COMPLETED.
These notes link each claim to its source. Some citations identify archived research reports that are no longer hosted on this site. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
Definitions
- Overused-word lists are the norm in public 'humanize' skills, e.g. a Tier 1 banned list of 18 words including delve, tapestry, pivotal, testament; such files embed the seeded tokens in the instruction file itself. (low confidence) (verified as of 2026-09-23) [source]
Problems, failure modes and limitations
- A mechanistic study of 40,000 samples reports that explicitly naming a forbidden word can raise its generation probability; priming failure accounts for 87.5% of negative-constraint violations and override failure for 12.5%. (medium confidence) [source]
- The same study finds violation probability tracks the model's intrinsic 'semantic pressure' toward the token (p = sigmoid(-2.40 + 2.27*P0)), so the risk is highest for high-prior tics such as delve, which are exactly the ones people list. (low confidence) [source]
Comparisons and alternatives
- Anthropic's prompting docs tell authors to say what to do instead of what not to do, and note that the formatting style of the prompt can influence response style, so instruction files should be written in the target voice. (high confidence) (verified as of 2026-09-23) [source]
- A workable lint design: scan instruction files for tokens on a tic list and classify each hit as ban-list entry, example text or incidental prose; flag examples and prose hits first, since they show the word as a model to copy rather than as a prohibition. This is inferred from the sources, not documented anywhere. (low confidence) [source]
Facts and statements
- Lexical overrepresentation (delve, intricate, underscore; 21 focal words in scientific abstracts) is not explained by architecture, algorithm or training data; RLHF is a suspect but evidence is mixed. The lint word list must therefore be empirical and per-model, not a fixed canon. (medium confidence) [source]
Children
- No children recorded.