Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910845365125120 |
|---|---|
| author | Baban, Hediyeh Pidapar, Sai A Nema, Aashutosh Lu, Sichen |
| author_facet | Baban, Hediyeh Pidapar, Sai A Nema, Aashutosh Lu, Sichen |
| contents | We introduce a novel multi-agent collaboration framework designed to enhance the accuracy and robustness of text classification models. Leveraging BERT as the primary classifier, our framework dynamically escalates low-confidence predictions to a specialized multi-agent system comprising Lexical, Contextual, Logic, Consensus, and Explainability agents. This collaborative approach allows for comprehensive analysis and consensus-driven decision-making, significantly improving classification performance across diverse text classification tasks. Empirical evaluations on benchmark datasets demonstrate that our framework achieves a 5.5% increase in accuracy compared to standard BERT-based classifiers, underscoring its effectiveness and academic novelty in advancing multi-agent systems within natural language processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18653 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT Baban, Hediyeh Pidapar, Sai A Nema, Aashutosh Lu, Sichen Computation and Language Artificial Intelligence We introduce a novel multi-agent collaboration framework designed to enhance the accuracy and robustness of text classification models. Leveraging BERT as the primary classifier, our framework dynamically escalates low-confidence predictions to a specialized multi-agent system comprising Lexical, Contextual, Logic, Consensus, and Explainability agents. This collaborative approach allows for comprehensive analysis and consensus-driven decision-making, significantly improving classification performance across diverse text classification tasks. Empirical evaluations on benchmark datasets demonstrate that our framework achieves a 5.5% increase in accuracy compared to standard BERT-based classifiers, underscoring its effectiveness and academic novelty in advancing multi-agent systems within natural language processing. |
| title | Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.18653 |