Table 5 Accuracy comparison of different models in proposer vs. aggregator roles within the MoA framework

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

Model

aggregator

proposer

Qwen2.5-7B-Instruct-Turbo

55.8

53.2

Mistral-7B-Instruct

47.4

51.6

Gemma-2-9b-it

49.6

58.2

Llama-3.2-11B-Vision

59.2

54.4

Llama-3.1-8B-Instruct-Turbo

46.8

53.4

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