Humans and Llama 3.3 70B both rate 'only' sentences higher than 'even' sentences, but the model's responses are uniformly extreme and lack human-like variability.
arXiv preprint arXiv:2603.18171 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Focus particles and scalar inferences across humans and language models
Humans and Llama 3.3 70B both rate 'only' sentences higher than 'even' sentences, but the model's responses are uniformly extreme and lack human-like variability.