Context-borne lexical contagion
Parent: Prompt-side control of LLM lexical tics · Published reference · snapshot 2026-09-23
↓ Facts as markdownall context files
Source-anchored research for Context-borne lexical contagion. 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
- Scoping: prompt wording effects on task performance are not simply predicted by word frequency or perplexity, and prompts transfer poorly across datasets and models; a single modal-verb change moved performance up to 17 points in the tested older models (2023, LLaMA/OPT). Do not extrapolate fixed contagion rules from vocabulary frequency. (low confidence) [source]
Problems, failure modes and limitations
- Repetition priming behaves differently in base LLMs, instruct LLMs and humans; instruction tuning appears to shift models toward more controlled processing, so contagion strength cannot be assumed identical across base and tuned models. (low confidence) (verified as of 2026-08-31) [source]
Comparisons and alternatives
- LLMs reliably repeat contextual content faithfully rather than relying only on internal parameters; RepeatLeakage exploits this to extract system prompts from GPT-Store apps and ChatGPT contexts, and the copy-from-context ability cannot be disabled without hurting core capability. (medium confidence) [source]
Facts and statements
- Anthropic's official prompting guide states that the formatting style used in a prompt may influence Claude's response style, and advises matching prompt style to desired output style; removing markdown from the prompt can reduce markdown in the output. (medium confidence) (verified as of 2026-09-23) [source]
- In controlled dative-completion experiments, structurally primed completions show greater lexico-semantic repetition of context, i.e. structural, lexical and semantic alignment reinforce each other during generation (EMNLP 2026 Findings, submitted 2026-09-03). (low confidence) (verified as of 2026-09-03) [source]
Children
- No children recorded.