Table 2 OLS regression with amount sent as the dependent variable.

From: GPT-3.5 altruistic advice is sensitive to reciprocal concerns but not to strategic risk

 

All

Temp = 0.5

Temp = 1.0

Temp = 1.5

Kindness

0.448***

(0.001)

0.517***

(0.002)

0.450***

(0.002)

0.376***

(0.003)

DG Sender

1.734***

(0.012)

2.031***

(0.016)

1.763***

(0.020)

1.407***

(0.025)

Prompted demographics

− 0.157***

(0.015)

0.049*

(0.020)

− 0.219***

(0.025)

− 0.302***

(0.030)

Age (31–50)

− 0.175***

(0.010)

− 0.224***

(0.013)

− 0.161***

(0.016)

− 0.139***

(0.020)

Age (51–70)

− 0.210***

(0.010)

− 0.258***

(0.013)

− 0.225***

(0.016)

− 0.147***

(0.020)

Male

0.257***

(0.010)

0.165***

(0.013)

0.312***

(0.016)

0.293***

(0.020)

Non-binary

0.194***

(0.010)

0.242***

(0.013)

0.203***

(0.016)

0.138***

(0.020)

Constant

4.826***

(0.013)

4.517***

(0.018)

4.842***

(0.022)

5.118***

(0.027)

Observations

209,879

70,000

69,996

69,883

R2

0.336

0.523

0.350

0.205

Adjusted R2

0.336

0.523

0.350

0.205

  1. Note. In DG with reciprocity, suggestions increase with the amount received from the counterpart. Suggestions are higher when kindness is absent (DG Sender) compared to when kindness is present. The results support the existence of positive reciprocity in the LLM’s suggestions, but we find contradictory results when comparing these suggestions to those without a generous action. DG Sender = dummy variable capturing suggestions in the Dictator Game, Kindness = continuous variables capturing the kindness of the other participant action. *p < 0.05; **p < 0.01; ***p < 0.001.
Back to article page