Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs. Tayyar Madabushi, H., Hudson, T., & Bonial, C. In Liu, K., Song, Y., Han, Z., Sifa, R., He, S., & Long, Y., editors, Proceedings of Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ COLING 2025, pages 107–119, Abu Dhabi, UAE, January, 2025. ELRA and ICCL.
Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs [link]Paper  abstract   bibtex   
Frame semantics provides an explanation for how we make use of conceptual frames, which encapsulate background knowledge and associations, to more completely understand the meanings of words within a context. Unfortunately, FrameNet, the only widely available implementation of frame semantics, is limited in both scale and coverage. Therefore, we introduce a novel mechanism for generating task-specific frames using large language models (LLMs), which we call Generative FrameNet. We demonstrate its effectiveness on a task that is highly relevant in the current landscape of LLMs: the interpretable storage and retrieval of factual information. Specifically, Generative Frames enable the extension of Retrieval-Augmented Generation (RAG), providing an interpretable framework for reducing inaccuracies in LLMs. We conduct experiments to demonstrate the effectiveness of this method both in terms of retrieval effectiveness as well as the relevance of the automatically generated frames and frame relations. Expert analysis shows that Generative Frames capture a more suitable level of semantic specificity than the frames from FrameNet. Thus, Generative Frames capture a notion of frame semantics that is closer to Fillmore`s originally intended definition, and offer potential for providing data-driven insights into Frame Semantics theory. Our results also show that this novel mechanism of Frame Semantic-based interpretable retrieval improves RAG for question answering with LLMs—outperforming a GPT-4 based baseline by up to 8 points. We provide open access to our data, including prompts and Generative FrameNet.
@inproceedings{tayyar_madabushi_generative_2025,
	address = {Abu Dhabi, UAE},
	title = {Generative {FrameNet}: {Scalable} and {Adaptive} {Frames} for {Interpretable} {Knowledge} {Storage} and {Retrieval} for {LLMs} {Powered} by {LLMs}},
	shorttitle = {Generative {FrameNet}},
	url = {https://aclanthology.org/2025.neusymbridge-1.11/},
	abstract = {Frame semantics provides an explanation for how we make use of conceptual frames, which encapsulate background knowledge and associations, to more completely understand the meanings of words within a context. Unfortunately, FrameNet, the only widely available implementation of frame semantics, is limited in both scale and coverage. Therefore, we introduce a novel mechanism for generating task-specific frames using large language models (LLMs), which we call Generative FrameNet. We demonstrate its effectiveness on a task that is highly relevant in the current landscape of LLMs: the interpretable storage and retrieval of factual information. Specifically, Generative Frames enable the extension of Retrieval-Augmented Generation (RAG), providing an interpretable framework for reducing inaccuracies in LLMs. We conduct experiments to demonstrate the effectiveness of this method both in terms of retrieval effectiveness as well as the relevance of the automatically generated frames and frame relations. Expert analysis shows that Generative Frames capture a more suitable level of semantic specificity than the frames from FrameNet. Thus, Generative Frames capture a notion of frame semantics that is closer to Fillmore`s originally intended definition, and offer potential for providing data-driven insights into Frame Semantics theory. Our results also show that this novel mechanism of Frame Semantic-based interpretable retrieval improves RAG for question answering with LLMs—outperforming a GPT-4 based baseline by up to 8 points. We provide open access to our data, including prompts and Generative FrameNet.},
	urldate = {2025-03-20},
	booktitle = {Proceedings of {Bridging} {Neurons} and {Symbols} for {Natural} {Language} {Processing} and {Knowledge} {Graphs} {Reasoning} @ {COLING} 2025},
	publisher = {ELRA and ICCL},
	author = {Tayyar Madabushi, Harish and Hudson, Taylor and Bonial, Claire},
	editor = {Liu, Kang and Song, Yangqiu and Han, Zhen and Sifa, Rafet and He, Shizhu and Long, Yunfei},
	month = jan,
	year = {2025},
	pages = {107--119},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021