Table 5 Impact of different temperature coefficients (t) performance of large language models.

From: Leveraging large language models and embedding representations for enhanced word similarity computation

Method

RG65

MC30

r

ρ

r

ρ

SBERT + Qwen-7B-Chat(t = 0.5)

0.8374

0.8089

0.8297

0.8429

SBERT + Qwen-7B-Chat(t = 0.7)

0.7935

0.7648

0.7939

0.8086

SBERT + Qwen-7B-Chat(t = 1)

0.7151

0.6974

0.7240

0.6613

Back to article page