| Challenge: | Existing methods for program generation use lightweight structures to represent high-level semantics and syntactic composition of a program. |
| Approach: | They propose a method for program generation based on semantic scaffolds . they use line-level natural language pseudocode annotations to search for programs . |
| Outcome: | The proposed method achieves 10% improvement in top-100 accuracy over the current state-of-the-art method. |
Similar Papers
Syntactic Scaffolds for Semantic Structures (D18-1)
Copied to clipboard
| Challenge: | Syntactic scaffolds avoid expensive syntactical processing at runtime . many systems have used syntastic dependency or phrase-based parsers as preprocessing for semantic analysis. |
| Approach: | They propose a multitask learning approach that uses a syntactic treebank to integrate syntaktic information into semantic tasks. |
| Outcome: | The proposed method improves on PropBank semantics, frame semantics and coreference resolution tasks. |
Natural Language Annotations for Reasoning about Program Semantics (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Xu et al., 2022) and Tafjord eet . al. 2021) have shown that programming assistants can explain their work by grounding natural language inference in code. |
| Approach: | They propose a dataset and protocol for annotating programs with natural language predicates at a finer granularity than code comments without relying on internal compiler representations. |
| Outcome: | The proposed method can be used to ground natural language inference in code without static analysis and without internal compiler representations. |
Analysis of Tree-Structured Architectures for Code Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Code generation is the task of generating code snippets from input user specifications written in natural language (NL). |
| Approach: | They evaluate the significance of input parse trees for code generation by using constituency-based parsers as input and an abstract syntax tree as the target. |
| Outcome: | The proposed models on a Python-based code generation dataset and a semantic parsing dataset show that constituency trees encoded using a structure-aware model improve performance. |
Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic Parsing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for table fact verification do not study generating latent programs from statements . current weakly supervised methods are limited due to huge search space with lots of spurious programs. |
| Approach: | They propose a structure-aware approach to do table fact verification by structure-based parsing . they leverage lexical features and structure features to generate program from statements . |
| Outcome: | The proposed method generates programs more accurately than existing parsers and achieves comparable performance to the SOTA on the large-scale benchmark TABFACT. |
CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow (2024.findings-acl)
Copied to clipboard
| Challenge: | Comprising 3,402 crafted examples, our dataset is designed for both model finetuning and standalone evaluation. |
| Approach: | They propose a dataset that provides examples that include a clarified intent, code snippets associated, and an average of three related unit tests. |
| Outcome: | The proposed dataset includes 3,402 hand-written examples and 3,121 unrefined examples. |
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space. |
| Approach: | They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations. |
| Outcome: | The proposed framework outperforms baselines while maintaining reasonable time and computational costs. |
ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Despite the critical role of software requirements, these criteria have not been studied actively in previous code generation works. |
| Approach: | They propose a framework that leverages in-context learning to organize and extrapolate unexpressed requirements from textual descriptions. |
| Outcome: | The proposed framework generates functional requirements from textual descriptions and extrapolates unexpressed requirements from them. |
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code. |
| Approach: | They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages . |
| Outcome: | The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation. |
Factorising AMR generation through syntax (N19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic annotation framework which abstracts away from the surface form of text to capture the core 'who did what to whom' structure. |
| Approach: | They propose to decompose the generation process into two steps: first generate a syntactic structure, and then generate the surface form. |
| Outcome: | The proposed approach generates meaning-preserving syntactic paraphrases of the same graph, as judged by humans. |
PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Using large language models to generate code has shown significant promise, but selecting effective examples to improve generation quality remains a challenging task. |
| Approach: | They propose a framework that utilizes algorithmic plans to identify and retrieve effective examples. |
| Outcome: | The proposed framework outperforms the state-of-the-art RAG methods in code generation even when the source and target languages match or differ. |