# On the (In)effectiveness of AMR Augmentation for Large Language Models

arXiv: https://arxiv.org/abs/2609.40121 · HTML: https://mlsanity.com/paper/2609.40121/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Graph Pre-training for AMR Parsing and Generation](https://mlsanity.com/paper/2203.07836/) (2022)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation](https://mlsanity.com/paper/2405.03085/) (2024)
- [Inducing and Using Alignments for Transition-based AMR Parsing](https://mlsanity.com/paper/2205.01464/) (2022)
- [Analyzing the Role of Semantic Representations in the Era of Large Language Models](https://mlsanity.com/paper/2405.01502/) (2024)
- [Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text](https://mlsanity.com/paper/1512.01587/) (2015)
- [Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM](https://mlsanity.com/paper/2407.04067/) (2024)
- [Can LLMs Interpret and Leverage Structured Linguistic Representations? A Case Study with AMRs](https://mlsanity.com/paper/2504.04745/) (2025)

## Abstract (arXiv)

While Abstract Meaning Representation (AMR) has historically improved performance on a range of NLP tasks, the benefit---or lack thereof---of AMR augmentation for modern LLMs is thus far unclear. In this paper, we attempt to reproduce recent work that reported substantial downstream gains from AMR augmentation, finding that these are likely due to specific choices in the experimental settings used: using a consistent and unified protocol for hyperparameter selection, we observe that text-only baselines consistently match or exceed the performance of AMR-augmented models. To investigate this null result, we introduce a perplexity-based probe measuring the degree to which AMR provides an LLM with supplemental relational knowledge not already available to the model. We find that AMR augmentation does not help LLMs improve their understanding of relational content in the sentence, indicating that augmenting these models with AMR offers no clear benefit on downstream tasks.