# LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models

arXiv: https://arxiv.org/abs/2506.05385 · HTML: https://mlsanity.com/paper/2506.05385/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Semantics-aware BERT for Language Understanding](https://mlsanity.com/paper/1909.02209/) (2019)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks](https://mlsanity.com/paper/1804.08313/) (2018)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [End-to-end Semantic Role Labeling with Neural Transition-based Model](https://mlsanity.com/paper/2101.00394/) (2021)
- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [Transition-based Semantic Dependency Parsing with Pointer Networks](https://mlsanity.com/paper/2005.13344/) (2020)
- [Semantic Role Labeling Guided Multi-turn Dialogue ReWriter](https://mlsanity.com/paper/2010.01417/) (2020)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [High-order Semantic Role Labeling](https://mlsanity.com/paper/2010.04641/) (2020)
- [KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server](https://mlsanity.com/paper/2410.05725/) (2024)
- [Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL](https://mlsanity.com/paper/2405.06410/) (2024)
- [A Sequence-to-Sequence Model for Semantic Role Labeling](https://mlsanity.com/paper/1807.03006/) (2018)
- [Semantic Role Labeling with Iterative Structure Refinement](https://mlsanity.com/paper/1909.03285/) (2019)
- [A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling](https://mlsanity.com/paper/1911.04641/) (2019)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models](https://mlsanity.com/paper/2502.08660/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations](https://mlsanity.com/paper/2512.00556/) (2025)

## Abstract (arXiv)

Semantic role labeling (SRL) is a crucial task of natural language processing (NLP). Although generative decoder-based large language models (LLMs) have achieved remarkable success across various NLP tasks, they still lag behind state-of-the-art encoder-decoder (BERT-like) models in SRL. In this work, we seek to bridge this gap by equipping LLMs for SRL with two mechanisms: (a) retrieval-augmented generation and (b) self-correction. The first mechanism enables LLMs to leverage external linguistic knowledge such as predicate and argument structure descriptions, while the second allows LLMs to identify and correct inconsistent SRL outputs. We conduct extensive experiments on three widely-used benchmarks of SRL (CPB1.0, CoNLL-2009, and CoNLL-2012). Results demonstrate that our method achieves state-of-the-art performance in both Chinese and English, marking the first successful application of LLMs to surpass encoder-decoder approaches in SRL.