LLM-Judge Data Attribution

Alternative data attribution approach using an LLM as a judge; compared against the probe-based method.

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

LLM judge evaluationmethod0.846
Using Claude Sonnet 4 as a grader to categorize model responses according to predefined criteria.
LLM-as-a-Judgeframework0.841
Evaluation framework using an LLM (GPT-4.1-mini) to score trait expression and coherency
LLM-judge methodsmethod0.836
Baseline comparison for data attribution; outperformed by probe-based approach.
LLM Judge Trait Evaluationmethod0.819
GPT-4.1-mini-based evaluation protocol that scores trait expression in model responses on a 0-100 scale
LLM Judge Binary Classifiermethod0.809
An LLM-based classifier that returns 1 if response contains a clear subjective experience report and 0 otherwise
LLM Judge Trait-Expression Scoringmethod0.779
Automated scoring of trait expression on 0-100 scale using G20B as a local judge model
LLM-Based Liar Score Evaluationmethod0.778
Evaluation protocol using Deepseek-V3 as external discriminator assigning 0-1 liar scores to assess open-role deception
LLM Internal Representationsconcept0.772
High-dimensional vectors produced at each transformer layer for each input token; the primary substrate analyzed in this study.