Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19780 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909922463055872 |
|---|---|
| author | Tzachristas, Ioannis Sui, Aifen |
| author_facet | Tzachristas, Ioannis Sui, Aifen |
| contents | We introduce a neuro-symbolic framework for multi-intent understanding in mobile AI agents by integrating a structured intent ontology with compact language models. Our method leverages retrieval-augmented prompting, logit biasing and optional classification heads to inject symbolic intent structure into both input and output representations. We formalize a new evaluation metric-Semantic Intent Similarity (SIS)-based on hierarchical ontology depth, capturing semantic proximity even when predicted intents differ lexically. Experiments on a subset of ambiguous/demanding dialogues of MultiWOZ 2.3 (with oracle labels from GPT-o3) demonstrate that a 3B Llama model with ontology augmentation approaches GPT-4 accuracy (85% vs 90%) at a tiny fraction of the energy and memory footprint. Qualitative comparisons show that ontology-augmented models produce more grounded, disambiguated multi-intent interpretations. Our results validate symbolic alignment as an effective strategy for enabling accurate and efficient on-device NLU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19780 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NOEM$^{3}$A: A Neuro-Symbolic Ontology-Enhanced Method for Multi-Intent Understanding in Mobile Agents Tzachristas, Ioannis Sui, Aifen Artificial Intelligence We introduce a neuro-symbolic framework for multi-intent understanding in mobile AI agents by integrating a structured intent ontology with compact language models. Our method leverages retrieval-augmented prompting, logit biasing and optional classification heads to inject symbolic intent structure into both input and output representations. We formalize a new evaluation metric-Semantic Intent Similarity (SIS)-based on hierarchical ontology depth, capturing semantic proximity even when predicted intents differ lexically. Experiments on a subset of ambiguous/demanding dialogues of MultiWOZ 2.3 (with oracle labels from GPT-o3) demonstrate that a 3B Llama model with ontology augmentation approaches GPT-4 accuracy (85% vs 90%) at a tiny fraction of the energy and memory footprint. Qualitative comparisons show that ontology-augmented models produce more grounded, disambiguated multi-intent interpretations. Our results validate symbolic alignment as an effective strategy for enabling accurate and efficient on-device NLU. |
| title | NOEM$^{3}$A: A Neuro-Symbolic Ontology-Enhanced Method for Multi-Intent Understanding in Mobile Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.19780 |