method
active
method:system-prompt-qa-spqaSystem Prompt QA (SPQA)
Training task: answer questions about target model propensities from activations in system-prompted transcripts.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Framework training LLMs to answer questions about externally-provided activation vectors
Datasets (1)
dataset
- Training dataset from LatentQA paper.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Imbuing method that prepends a ~50-word personality description as the system message
- Using system prompts to instruct models to adopt a persona; used as baseline comparison against character training
- Systematic modification of system prompt elements to identify which are necessary for alignment faking
- Task-aware prompt optimization framework that refines prompts through feedback-driven critique and synthesis
- Hand-written and synthetically extended prompts tied to specific constitution assertions, used to improve sample efficiency of distillation
- A prompt framing requesting a representative sample from a distribution rather than a single instance, which is the key insight behind VS
- Method of providing training information in-context via a system prompt to elicit alignment faking
- Testing five phrasings of the self-referential prompt to confirm robustness to wording variation