# Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation

arXiv: https://arxiv.org/abs/2503.22776 · HTML: https://mlsanity.com/paper/2503.22776/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 94 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 30 of 61)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [code2vec: Learning Distributed Representations of Code](https://mlsanity.com/paper/1803.09473/) (2018)

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

- [ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation](https://mlsanity.com/paper/2604.03922/) (2026)
- [Design-Specification Tiling for ICL-based CAD Code Generation](https://mlsanity.com/paper/2603.12712/) (2026)
- [CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification](https://mlsanity.com/paper/2609.07434/) (2026)

## Abstract (arXiv)

Code translation migrates codebases across programming languages. Recently, large language models (LLMs) have achieved significant advancements in software mining. However, handling the syntactic structure of source code remains a challenge. Classic syntax-aware methods depend on intricate model architectures and loss functions, rendering their integration into LLM training resource-intensive. This paper employs in-context learning (ICL), which directly integrates task exemplars into the input context, to post-incorporate code structural knowledge into pre-trained LLMs. We revisit exemplar selection in ICL from an information-theoretic perspective, proposing that list-wise selection based on information coverage is more precise and general objective than traditional methods based on combining similarity and diversity. To address the challenges of quantifying information coverage, we introduce a surrogate measure, Coverage of Abstract Syntax Tree (CAST). Furthermore, we formulate the NP-hard CAST maximization for exemplar selection and prove that it is a standard submodular maximization problem. Therefore, we propose a greedy algorithm for CAST submodular maximization, which theoretically guarantees a (1-1/e)-approximate solution in polynomial time complexity. Our method is the first training-free and model-agnostic approach to post-incorporate code structural knowledge into existing LLMs at test time. Experimental results show that our method significantly improves LLMs performance and reveals two meaningful insights: 1) Code structural knowledge can be effectively post-incorporated into pre-trained LLMs during inference, despite being overlooked during training; 2) Scaling up model size or training data does not lead to the emergence of code structural knowledge, underscoring the necessity of explicitly considering code syntactic structure.