Table 4 Impact of feedback generation operators on model performance. This table shows the effect of enabling or disabling the Problem Formulation Operator and Programming Operator during feedback generation, under a fixed parameter setting (P=10, Q=10, R=5) and 500 total optimisation steps. The highest test dataset accuracy is achieved when both operators are active. Removing either operator results in a notable performance drop, highlighting the complementary role of both operator types in generating effective feedback.
From: Feedback-integrated prompt optimiser for problem formulation
Parameter setting (P, Q, R) | Availability of problem formulation operator | Availability of programming operator | Total number of steps | Test dataset accuracy % |
|---|---|---|---|---|
(10, 10, 5) | \({\checkmark }\) | \({\checkmark }\) | 500 | 54% |
(10, 10, 5) | ✗ | \({\checkmark }\) | 500 | 31% |
(10, 10, 5) | \({\checkmark }\) | ✗ | 500 | 37% |
