Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2409.11589 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929503398264832 |
|---|---|
| author | Vakharia, Priyesh Kufeldt, Abigail Meyers, Max Lane, Ian Gilpin, Leilani |
| author_facet | Vakharia, Priyesh Kufeldt, Abigail Meyers, Max Lane, Ian Gilpin, Leilani |
| contents | Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering Vakharia, Priyesh Kufeldt, Abigail Meyers, Max Lane, Ian Gilpin, Leilani Computation and Language Artificial Intelligence I.2 Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization. |
| title | ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering |
| topic | Computation and Language Artificial Intelligence I.2 |
| url | https://arxiv.org/abs/2409.11589 |