Gyan: An Explainable Neuro-Symbolic Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917490188091392 |
|---|---|
| author | Srinivasan, Venkat Jatav, Vishaal Chandrababu, Anushka Sharma, Geetika |
| author_facet | Srinivasan, Venkat Jatav, Vishaal Chandrababu, Anushka Sharma, Geetika |
| contents | Transformer based pre-trained large language models have become ubiquitous. There is increasing evidence to suggest that even with large scale pre-training, these models do not capture complete compositional context and certainly not, the full human analogous context. Besides, by the very nature of the architecture, these models hallucinate, are difficult to maintain, are not easily interpretable and require enormous compute resources for training and inference. Here, we describe Gyan, an explainable language model based on a novel non-transformer architecture, without any of these limitations. Gyan achieves SOTA performance on 3 widely cited data sets and superior performance on two proprietary data sets. The novel architecture decouples the language model from knowledge acquisition and representation. The model draws on rhetorical structure theory, semantic role theory and knowledge-based computational linguistics. Gyan's meaning representation structure captures the complete compositional context and attempts to mimic humans by expanding the context to a 'world model'. AI model adoption critically depends on trust and transparency especially in mission critical use cases. Collectively, our results demonstrate that it is possible to create models which are trustable and reliable for mission critical tasks. We believe our work has tremendous potential for guiding the development of transparent and trusted architectures for language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04759 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gyan: An Explainable Neuro-Symbolic Language Model Srinivasan, Venkat Jatav, Vishaal Chandrababu, Anushka Sharma, Geetika Computation and Language Artificial Intelligence Emerging Technologies Machine Learning I.2.0; I.2.1; I.2.3; I.2.4; I.2.6; I.2.7; I.2.8; I.7 Transformer based pre-trained large language models have become ubiquitous. There is increasing evidence to suggest that even with large scale pre-training, these models do not capture complete compositional context and certainly not, the full human analogous context. Besides, by the very nature of the architecture, these models hallucinate, are difficult to maintain, are not easily interpretable and require enormous compute resources for training and inference. Here, we describe Gyan, an explainable language model based on a novel non-transformer architecture, without any of these limitations. Gyan achieves SOTA performance on 3 widely cited data sets and superior performance on two proprietary data sets. The novel architecture decouples the language model from knowledge acquisition and representation. The model draws on rhetorical structure theory, semantic role theory and knowledge-based computational linguistics. Gyan's meaning representation structure captures the complete compositional context and attempts to mimic humans by expanding the context to a 'world model'. AI model adoption critically depends on trust and transparency especially in mission critical use cases. Collectively, our results demonstrate that it is possible to create models which are trustable and reliable for mission critical tasks. We believe our work has tremendous potential for guiding the development of transparent and trusted architectures for language models. |
| title | Gyan: An Explainable Neuro-Symbolic Language Model |
| topic | Computation and Language Artificial Intelligence Emerging Technologies Machine Learning I.2.0; I.2.1; I.2.3; I.2.4; I.2.6; I.2.7; I.2.8; I.7 |
| url | https://arxiv.org/abs/2605.04759 |