A visual analytics workspace uses LLM explanation and verification agents to semi-automatically annotate and perturbation-check mapper graph elements of BERT embeddings, replicating known layer-wise linguistic patterns.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
A visual analytics workspace uses LLM explanation and verification agents to semi-automatically annotate and perturbation-check mapper graph elements of BERT embeddings, replicating known layer-wise linguistic patterns.