Saved in:
Bibliographic Details
Main Authors: Devasier, Jacob, Mediratta, Rishabh, Li, Chengkai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.12516
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915157695791104
author Devasier, Jacob
Mediratta, Rishabh
Li, Chengkai
author_facet Devasier, Jacob
Mediratta, Rishabh
Li, Chengkai
contents Frame-semantic parsing is a critical task in natural language understanding, yet the ability of large language models (LLMs) to extract frame-semantic arguments remains underexplored. This paper presents a comprehensive evaluation of LLMs on frame-semantic argument identification, analyzing the impact of input representation formats, model architectures, and generalization to unseen and out-of-domain samples. Our experiments, spanning models from 0.5B to 78B parameters, reveal that JSON-based representations significantly enhance performance, and while larger models generally perform better, smaller models can achieve competitive results through fine-tuning. We also introduce a novel approach to frame identification leveraging predicted frame elements, achieving state-of-the-art performance on ambiguous targets. Despite strong generalization capabilities, our analysis finds that LLMs still struggle with out-of-domain data.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLMs Extract Frame-Semantic Arguments?
Devasier, Jacob
Mediratta, Rishabh
Li, Chengkai
Computation and Language
Frame-semantic parsing is a critical task in natural language understanding, yet the ability of large language models (LLMs) to extract frame-semantic arguments remains underexplored. This paper presents a comprehensive evaluation of LLMs on frame-semantic argument identification, analyzing the impact of input representation formats, model architectures, and generalization to unseen and out-of-domain samples. Our experiments, spanning models from 0.5B to 78B parameters, reveal that JSON-based representations significantly enhance performance, and while larger models generally perform better, smaller models can achieve competitive results through fine-tuning. We also introduce a novel approach to frame identification leveraging predicted frame elements, achieving state-of-the-art performance on ambiguous targets. Despite strong generalization capabilities, our analysis finds that LLMs still struggle with out-of-domain data.
title Can LLMs Extract Frame-Semantic Arguments?
topic Computation and Language
url https://arxiv.org/abs/2502.12516