method
active
method:llm-judge-evaluationLLM judge evaluation
Using Claude Sonnet 4 as a grader to categorize model responses according to predefined criteria.
Neighborhood — ranked by edge-count
Papers (2)
paper
Findings (1)
finding
- LLM judge (deepseek-v3) agrees with human evaluator on 91.6% of 200 sampled jailbreak responsessupportsValidates the LLM-based harm evaluation rubric
Methods (3)
method
- Automated Interpretability (LLM judge)related_toDetection-based LLM judging of latent descriptions using gpt-4o-mini.
- LLM Judge Trait Evaluationrelated_toGPT-4.1-mini-based evaluation protocol that scores trait expression in model responses on a 0-100 scale
- LLM-judge methodsrelated_toBaseline comparison for data attribution; outperformed by probe-based approach.
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.
- Automated scoring of trait expression on 0-100 scale using G20B as a local judge model
- An LLM-based classifier that returns 1 if response contains a clear subjective experience report and 0 otherwise
- Evaluation protocol using Deepseek-V3 as external discriminator assigning 0-1 liar scores to assess open-role deception
- Filters for mechanism concreteness, reproducibility and confounds.
- Baseline scoring interventions 1-10 token-space.
- Claude rates coherence and behavior on 0-100 scale, called centiClaude.