# Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding

arXiv: https://arxiv.org/abs/2504.00409 · HTML: https://mlsanity.com/paper/2504.00409/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 19 of 19)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [A Survey of Machine Learning for Big Code and Naturalness](https://mlsanity.com/paper/1709.06182/) (2017)
- [Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners](https://mlsanity.com/paper/2305.14825/) (2023)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [Citation-Enhanced Generation for LLM-based Chatbots](https://mlsanity.com/paper/2402.16063/) (2024)
- [Semantically Enhanced Software Traceability Using Deep Learning Techniques](https://mlsanity.com/paper/1804.02438/) (2018)
- [Language Models As Semantic Indexers](https://mlsanity.com/paper/2310.07815/) (2023)
- [CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks](https://mlsanity.com/paper/2310.14623/) (2023)
- [Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks](https://mlsanity.com/paper/2407.02310/) (2024)
- [Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach](https://mlsanity.com/paper/2501.11041/) (2025)
- [Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL](https://mlsanity.com/paper/2405.06410/) (2024)
- [Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering](https://mlsanity.com/paper/2212.10696/) (2022)
- [LLMs' Understanding of Natural Language Revealed](https://mlsanity.com/paper/2407.19630/) (2024)
- [Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques](https://mlsanity.com/paper/2410.13498/) (2024)

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

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph](https://mlsanity.com/paper/2510.10976/) (2025)
- [Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration](https://mlsanity.com/paper/2510.10824/) (2025)
- [Comparing Developer and LLM Biases in Code Evaluation](https://mlsanity.com/paper/2603.24586/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have greatly improved their capability in performing NLP tasks. However, deeper semantic understanding, contextual coherence, and more subtle reasoning are still difficult to obtain. The paper discusses state-of-the-art methodologies that advance LLMs with more advanced NLU techniques, such as semantic parsing, knowledge integration, and contextual reinforcement learning. We analyze the use of structured knowledge graphs, retrieval-augmented generation (RAG), and fine-tuning strategies that match models with human-level understanding. Furthermore, we address the incorporation of transformer-based architectures, contrastive learning, and hybrid symbolic-neural methods that address problems like hallucinations, ambiguity, and inconsistency in the factual perspectives involved in performing complex NLP tasks, such as question-answering text summarization and dialogue generation. Our findings show the importance of semantic precision for enhancing AI-driven language systems and suggest future research directions to bridge the gap between statistical language models and true natural language understanding.