Table 7 Accuracy comparison of different discriminator models in the SLM-MATRIX framework using LLaMA-3.1-8B-Instruct-Turbo as the generator

From: SLM-MATRIX: a multi-agent trajectory reasoning and verification framework for enhancing language models in materials data extraction

Model

Discriminator

Accuracy (%)

Llama-3.1-8B-Instruct-Turbo

Majority Voting (Maj)

87.49

Qwen2.5-7B-Instruct-Turbo

90.14

Mistral-7B-Instruct

85.29

gemma-2-9b-it

89.61

Llama-3.2-11B-Vision

90.83

Llama-3.1-8B-Instruct-Turbo

88.40

  1. The bold values highlight the best-performing result within a given comparison group.
Back to article page