@inproceedings{tayyar-madabushi-etal-2025-generative,
title = "Generative {F}rame{N}et: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for {LLM}s Powered by {LLM}s",
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",
booktitle = "Proceedings of Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ COLING 2025",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2025.neusymbridge-1.11/",
pages = "107--119",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tayyar-madabushi-etal-2025-generative">
<titleInfo>
<title>Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Hudson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ COLING 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafet</namePart>
<namePart type="family">Sifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunfei</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">tayyar-madabushi-etal-2025-generative</identifier>
<location>
<url>https://aclanthology.org/2025.neusymbridge-1.11/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>107</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs
%A Tayyar Madabushi, Harish
%A Hudson, Taylor
%A Bonial, Claire
%Y Liu, Kang
%Y Song, Yangqiu
%Y Han, Zhen
%Y Sifa, Rafet
%Y He, Shizhu
%Y Long, Yunfei
%S Proceedings of Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ COLING 2025
%D 2025
%8 January
%I ELRA and ICCL
%C Abu Dhabi, UAE
%F tayyar-madabushi-etal-2025-generative
%X 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.
%U https://aclanthology.org/2025.neusymbridge-1.11/
%P 107-119
Markdown (Informal)
[Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs](https://aclanthology.org/2025.neusymbridge-1.11/) (Tayyar Madabushi et al., NeusymBridge 2025)
ACL