DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914964164313088 |
|---|---|
| author | Luong, Vinh Dinh, Sang Raghavan, Shruti Nguyen, William Nguyen, Zooey Le, Quynh Vo, Hung Maegaito, Kentaro Nguyen, Loc Nguyen, Thao Ha, Anh Hai Nguyen, Christopher |
| author_facet | Luong, Vinh Dinh, Sang Raghavan, Shruti Nguyen, William Nguyen, Zooey Le, Quynh Vo, Hung Maegaito, Kentaro Nguyen, Loc Nguyen, Thao Ha, Anh Hai Nguyen, Christopher |
| contents | Large Language Models (LLMs) have shown remarkable capabilities, but their inherent probabilistic nature often leads to inconsistency and inaccuracy in complex problem-solving tasks. This paper introduces DANA (Domain-Aware Neurosymbolic Agent), an architecture that addresses these issues by integrating domain-specific knowledge with neurosymbolic approaches. We begin by analyzing current AI architectures, including AutoGPT, LangChain ReAct and OpenAI's ChatGPT, through a neurosymbolic lens, highlighting how their reliance on probabilistic inference contributes to inconsistent outputs. In response, DANA captures and applies domain expertise in both natural-language and symbolic forms, enabling more deterministic and reliable problem-solving behaviors. We implement a variant of DANA using Hierarchical Task Plans (HTPs) in the open-source OpenSSA framework. This implementation achieves over 90\% accuracy on the FinanceBench financial-analysis benchmark, significantly outperforming current LLM-based systems in both consistency and accuracy. Application of DANA in physical industries such as semiconductor shows that its flexible architecture for incorporating knowledge is effective in mitigating the probabilistic limitations of LLMs and has potential in tackling complex, real-world problems that require reliability and precision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02823 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy Luong, Vinh Dinh, Sang Raghavan, Shruti Nguyen, William Nguyen, Zooey Le, Quynh Vo, Hung Maegaito, Kentaro Nguyen, Loc Nguyen, Thao Ha, Anh Hai Nguyen, Christopher Artificial Intelligence Machine Learning Large Language Models (LLMs) have shown remarkable capabilities, but their inherent probabilistic nature often leads to inconsistency and inaccuracy in complex problem-solving tasks. This paper introduces DANA (Domain-Aware Neurosymbolic Agent), an architecture that addresses these issues by integrating domain-specific knowledge with neurosymbolic approaches. We begin by analyzing current AI architectures, including AutoGPT, LangChain ReAct and OpenAI's ChatGPT, through a neurosymbolic lens, highlighting how their reliance on probabilistic inference contributes to inconsistent outputs. In response, DANA captures and applies domain expertise in both natural-language and symbolic forms, enabling more deterministic and reliable problem-solving behaviors. We implement a variant of DANA using Hierarchical Task Plans (HTPs) in the open-source OpenSSA framework. This implementation achieves over 90\% accuracy on the FinanceBench financial-analysis benchmark, significantly outperforming current LLM-based systems in both consistency and accuracy. Application of DANA in physical industries such as semiconductor shows that its flexible architecture for incorporating knowledge is effective in mitigating the probabilistic limitations of LLMs and has potential in tackling complex, real-world problems that require reliability and precision. |
| title | DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.02823 |