NLI benchmarks still discriminate between LLMs of different sizes and are not saturated, while the Jensen-Shannon distance between model and human label distributions shrinks with scale.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models
NLI benchmarks still discriminate between LLMs of different sizes and are not saturated, while the Jensen-Shannon distance between model and human label distributions shrinks with scale.