method
active
method:rejection-samplingRejection sampling
A technique to filter model outputs; Redwood Research's project mentioned.
Neighborhood — ranked by edge-count
Artifacts (1)
artifact
- Simulators (LessWrong post)mentionsThe paper being extracted.
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.
- The mechanism by which LLMs generate text: drawing a token from the next-token distribution and appending it to context repeatedly
- A Bayesian exploration strategy that samples from the posterior distribution over model parameters to decide actions.
- Baseline using Binomial(k,p) draws from precomputed rollouts.
- The paper's proposed training-free prompting strategy that prompts the model to verbalize a probability distribution over a set of responses rather than generating a single response
- Temperature=0.8 sampled decoding for self-report; reduces collapse moderately but remains discrete and noisy
- Dividing feature activation spectrum into 11 evenly-spaced intervals and sampling uniformly to evaluate monosemanticity across activation levels
- The percentage of harmful requests that a model refuses to answer, a common safety metric.
- Test-time compute scaling guided by reward probes with majority-vote over action.