Table 7 Comparison with modern transformer baselines for department routing.

From: A zero-shot LLM framework for multimodal grievance classification, urgency scoring, and abuse detection in civic feedback systems

Model

Accuracy (%)

Latency (ms)

Training required

TF–IDF + SVM

87.1

21

Yes

BERT-base (fine-tuned)

94.1

128

Yes

RoBERTa-base (fine-tuned)

94.8

141

Yes

MobileBERT (zero-shot, proposed)

92.4

19

No

Back to article page