# SR-LLM: Rethinking the Structured Representation in Large Language Model

arXiv: https://arxiv.org/abs/2502.14352 · HTML: https://mlsanity.com/paper/2502.14352/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [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)
- [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)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Datasets for Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2402.18041/) (2024)
- [A Graph-to-Sequence Model for AMR-to-Text Generation](https://mlsanity.com/paper/1805.02473/) (2018)
- [Graph Pre-training for AMR Parsing and Generation](https://mlsanity.com/paper/2203.07836/) (2022)
- [Do Syntax Trees Help Pre-trained Transformers Extract Information?](https://mlsanity.com/paper/2008.09084/) (2020)
- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [An Incremental Parser for Abstract Meaning Representation](https://mlsanity.com/paper/1608.06111/) (2016)
- [Formal Specifications from Natural Language](https://mlsanity.com/paper/2206.01962/) (2022)
- [Logical Fallacy Detection](https://mlsanity.com/paper/2202.13758/) (2022)
- [Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation](https://mlsanity.com/paper/2405.03085/) (2024)
- [LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic](https://mlsanity.com/paper/2406.17663/) (2024)
- [Analyzing the Role of Semantic Representations in the Era of Large Language Models](https://mlsanity.com/paper/2405.01502/) (2024)
- [Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints](https://mlsanity.com/paper/2409.14469/) (2024)
- [Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM](https://mlsanity.com/paper/2407.04067/) (2024)

## Built on by (most cited first, 3 of 3)

- [Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination](https://mlsanity.com/paper/2504.20643/) (2025)
- [NLD-LLM: A systematic framework for evaluating small language transformer models on natural language description](https://mlsanity.com/paper/2510.05139/) (2025)
- [LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation](https://mlsanity.com/paper/2504.16408/) (2025)

## Abstract (arXiv)

Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to integrate structured representation into LLMs via a zero-shot setting yielded inferior performance. We hypothesize that such a decline stems from the structure information being passed into LLMs in a code format unfamiliar to LLMs' training corpora. Consequently, we propose SR-LLM, an innovative framework with two settings to explore a superior way of integrating structured representation with LLMs from training-free and training-dependent perspectives. The former integrates structural information through natural language descriptions in LLM prompts, whereas its counterpart augments the model's inference capability through fine-tuning on linguistically described structured representations. Performance improvements were observed in widely downstream datasets, with particularly notable gains of 3.17% and 12.38% in PAWS. To the best of our knowledge, this work represents the pioneering demonstration that leveraging structural representations can substantially enhance LLMs' inference capability. We hope that our work sheds light and encourages future research to enhance the reasoning and interoperability of LLMs by structure data.