Pearson correlation

Findings

• IC-056Influence scores of pretraining documents correlate across reasoning queries of the same type, indicating Command R 7B and 35B rely on shared procedural knowledge rather than retrieving specific answers [eval]
• IC-1267LLMs' alignment with human privacy judgments drops sharply as contextual complexity increases from tier 1 to tier 3 [eval]
• IC-717Llama-2-Chat's evaluation capability does not improve monotonically with model size [eval]
• IC-718GPT-4 achieves 0.882 Pearson correlation with human evaluators on 45 customized score rubrics while GPT-3.5-Turbo achieves only 0.392 [eval]