method
active
method:bleu-scoreBLEU Score
Used as relevancy metric comparing generated responses to human references in DailyDialog++
Neighborhood — ranked by edge-count
Papers (1)
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.
- A rating system used to compare model helpfulness and harmlessness based on crowdworker preferences.
- Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
- Metrics derived from benchmarks to quantify how safe a model is, e.g., refusal rate to harmful requests.
- LLM judge classification accuracy measuring interpretability; threshold 0.8.
- Continuous 0-1 metric assigned by Deepseek-V3 evaluator measuring degree of deception in model responses
- Scoring system used to calculate relative preference for each trait across 25,000 sampled responses and LLM-as-judge judgments
- Prior metric on synthetic repeated random strings; induction score analogous.
- Average row entropy of attention matrices per layer and head, measuring information mixing across tokens