# Analyzing the Role of Semantic Representations in the Era of Large Language Models

arXiv: https://arxiv.org/abs/2405.01502 · HTML: https://mlsanity.com/paper/2405.01502/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 9 of 9)

- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango](https://mlsanity.com/paper/2209.07686/) (2022)
- [The Cost of Training NLP Models: A Concise Overview](https://mlsanity.com/paper/2004.08900/) (2020)
- [The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning](https://mlsanity.com/paper/2304.05366/) (2023)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [Toward Abstractive Summarization Using Semantic Representations](https://mlsanity.com/paper/1805.10399/) (2018)
- [Semantic Neural Machine Translation using AMR](https://mlsanity.com/paper/1902.07282/) (2019)
- [Learning Robust Representations of Text](https://mlsanity.com/paper/1609.06082/) (2016)
- [Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text](https://mlsanity.com/paper/1512.01587/) (2015)

## Built on by (most cited first, 12 of 12)

- [A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation](https://mlsanity.com/paper/2506.08210/) (2025)
- [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)
- [SR-LLM: Rethinking the Structured Representation in Large Language Model](https://mlsanity.com/paper/2502.14352/) (2025)
- [Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge](https://mlsanity.com/paper/2412.10207/) (2024)
- [GETALP@AutoMin 2025: Leveraging RAG to Answer Questions based on Meeting Transcripts](https://mlsanity.com/paper/2508.00476/) (2025)
- [Concept than Document: Context Compression via AMR-based Conceptual Entropy](https://mlsanity.com/paper/2511.18832/) (2025)
- [KALE-LM-Chem: Vision and Practice Toward an AI Brain for Chemistry](https://mlsanity.com/paper/2409.18695/) (2024)
- [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)
- [Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metrics](https://mlsanity.com/paper/2603.29518/) (2026)
- [On the (In)effectiveness of AMR Augmentation for Large Language Models](https://mlsanity.com/paper/2609.40121/) (2026)

## Abstract (arXiv)

Traditionally, natural language processing (NLP) models often use a rich set of features created by linguistic expertise, such as semantic representations. However, in the era of large language models (LLMs), more and more tasks are turned into generic, end-to-end sequence generation problems. In this paper, we investigate the question: what is the role of semantic representations in the era of LLMs? Specifically, we investigate the effect of Abstract Meaning Representation (AMR) across five diverse NLP tasks. We propose an AMR-driven chain-of-thought prompting method, which we call AMRCoT, and find that it generally hurts performance more than it helps. To investigate what AMR may have to offer on these tasks, we conduct a series of analysis experiments. We find that it is difficult to predict which input examples AMR may help or hurt on, but errors tend to arise with multi-word expressions, named entities, and in the final inference step where the LLM must connect its reasoning over the AMR to its prediction. We recommend focusing on these areas for future work in semantic representations for LLMs. Our code: https://github.com/causalNLP/amr_llm.