# Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

arXiv: https://arxiv.org/abs/2407.04067 · HTML: https://mlsanity.com/paper/2407.04067/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024)
- [Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://mlsanity.com/paper/1704.08381/) (2017)
- [Graph Pre-training for AMR Parsing and Generation](https://mlsanity.com/paper/2203.07836/) (2022)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Leveraging Abstract Meaning Representation for Knowledge Base Question Answering](https://mlsanity.com/paper/2012.01707/) (2020)
- [Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models](https://mlsanity.com/paper/2311.09278/) (2023)
- [Learning To Split and Rephrase From Wikipedia Edit History](https://mlsanity.com/paper/1808.09468/) (2018)
- [Split and Rephrase](https://mlsanity.com/paper/1707.06971/) (2017)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Simple and Effective Text Simplification Using Semantic and Neural Methods](https://mlsanity.com/paper/1810.05104/) (2018)
- [Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models](https://mlsanity.com/paper/2404.02575/) (2024)
- [BiSECT: Learning to Split and Rephrase Sentences with Bitexts](https://mlsanity.com/paper/2109.05006/) (2021)
- [Analyzing the Role of Semantic Representations in the Era of Large Language Models](https://mlsanity.com/paper/2405.01502/) (2024)
- [MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions](https://mlsanity.com/paper/1909.12131/) (2019)
- [ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences](https://mlsanity.com/paper/2106.12027/) (2021)
- [Split and Rephrase with Large Language Models](https://mlsanity.com/paper/2312.11075/) (2023)
- [Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation](https://mlsanity.com/paper/2404.03278/) (2024)
- [Discourse-Aware Text Simplification: From Complex Sentences to Linked Propositions](https://mlsanity.com/paper/2308.00425/) (2023)

## Built on by (most cited first, 4 of 4)

- [SR-LLM: Rethinking the Structured Representation in Large Language Model](https://mlsanity.com/paper/2502.14352/) (2025)
- [When Does Meaning Backfire? Investigating the Role of AMRs in NLI](https://mlsanity.com/paper/2506.14613/) (2025)
- [SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation](https://mlsanity.com/paper/2507.13381/) (2025)
- [On the (In)effectiveness of AMR Augmentation for Large Language Models](https://mlsanity.com/paper/2609.40121/) (2026)

## Abstract (arXiv)

Symbolic sentence meaning representations, such as AMR (Abstract Meaning Representation) provide expressive and structured semantic graphs that act as intermediates that simplify downstream NLP tasks. However, the instruction-following capability of large language models (LLMs) offers a shortcut to effectively solve NLP tasks, questioning the utility of semantic graphs. Meanwhile, recent work has also shown the difficulty of using meaning representations merely as a helpful auxiliary for LLMs. We revisit the position of semantic graphs in syntactic simplification, the task of simplifying sentence structures while preserving their meaning, which requires semantic understanding, and evaluate it on a new complex and natural dataset. The AMR-based method that we propose, AMRS3, demonstrates that state-of-the-art meaning representations can lead to easy-to-implement simplification methods with competitive performance and unique advantages in cost, interpretability, and generalization. With AMRS3 as an anchor, we discover that syntactic simplification is a task where semantic graphs are helpful in LLM prompting. We propose AMRCoC prompting that guides LLMs to emulate graph algorithms for explicit symbolic reasoning on AMR graphs, and show its potential for improving LLM on semantic-centered tasks like syntactic simplification.