method
active
method:llm-as-a-judge-baseline-gemma-self-gradingLLM-as-a-Judge baseline (Gemma self-grading)
Baseline scoring interventions 1-10 token-space.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- At n=256 best-of-n, probe scoring outperforms Gemma LLM-judge scoring by nearly 15 percentage pointsassociated_withTest-time scaling comparison.
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.
- Evaluation framework using an LLM (GPT-4.1-mini) to score trait expression and coherency
- Alternative data attribution approach using an LLM as a judge; compared against the probe-based method.
- Detection-based LLM judging of latent descriptions using gpt-4o-mini.
- An LLM-based classifier that returns 1 if response contains a clear subjective experience report and 0 otherwise
- Using Claude Sonnet 4 as a grader to categorize model responses according to predefined criteria.
- Manually curated, triplicate-consensus judge used as ground truth.
- Automated scoring of trait expression on 0-100 scale using G20B as a local judge model
- GPT-4.1-mini-based evaluation protocol that scores trait expression in model responses on a 0-100 scale