A hierarchical team of LLM agents with specialized roles achieved 60% accuracy and 73.3% F1 on a 200 sample German credit task, beating single model baselines.
- Include relevant aspects such as financial stability, spending habits, risk tolerance, and any contextual nuances derived from the input data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MASCA: LLM based-Multi Agents System for Credit Assessment
A hierarchical team of LLM agents with specialized roles achieved 60% accuracy and 73.3% F1 on a 200 sample German credit task, beating single model baselines.