method
active
method:bertscoreBERTScore
Token-level BERT embedding similarity metric used for both diversity comparison and relevancy evaluation
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.
- Sentence-level semantic similarity metric repurposed as diversity measure in Tevet and Berant 2021
- A body of research studying internal representations of transformer language models, especially BERT, including probing methods and attention head analysis
- Cosine similarity between BERT sentence embeddings; top automatic baseline for semantic diversity
- Prior work on atomic factual evaluation that motivates the atomic unit approach in this paper
- Prior metric on synthetic repeated random strings; induction score analogous.
- LLM judge classification accuracy measuring interpretability; threshold 0.8.
- Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
- GPT-4o scored 0-100 metric where lower values indicate more misaligned behavior on open-ended evaluation prompts