Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?

• URL: http://arxiv.org/abs/2503.05507v1
• Date: Fri, 07 Mar 2025 15:23:13 GMT
• Title: Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?
• Authors: Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Yueyi Xiao, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Bin Chen, Yingfei Xiong,
• Abstract summary: Grammar serves as a cornerstone in programming languages and software engineering.<n>Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models.<n>We develop a series of billion-scale GrammarCoder models, incorporating grammar rules in the code generation process.
• Score: 29.690921649662744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. However, as language models scale to the billion level or beyond, syntax-level errors become rare, making it unclear whether grammar information still provides performance benefits. To explore this, we develop a series of billion-scale GrammarCoder models, incorporating grammar rules in the code generation process. Experiments on HumanEval (+) and MBPP (+) demonstrate a notable improvement in code generation accuracy. Further analysis shows that grammar-based representations enhance LLMs' ability to discern subtle code differences, reducing semantic errors caused by minor variations. These findings suggest that grammar-based code representations remain valuable even in billion-scale models, not only by maintaining syntax correctness but also by improving semantic differentiation.

Related papers

• Insights from Benchmarking Frontier Language Models on Web App Code Generation [1.7268889851975326]
  This paper presents insights from evaluating 16 frontier large language models (LLMs) on the WebApp1K benchmark. The results reveal that while all models possess similar underlying knowledge, their performance is differentiated by the frequency of mistakes they make.
  arXiv  Detail & Related papers  (2024-09-08T18:24:26Z)
• Grammar-based Game Description Generation using Large Language Models [12.329521804287259]
  Game Description Language (GDL) provides a standardized way to express diverse games in a machine-readable format.<n>This paper presents a novel framework that leverages Large Language Models (LLMs) to generate grammatically accurate game descriptions from natural language.
  arXiv  Detail & Related papers  (2024-07-24T16:36:02Z)
• Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks [0.996023506058745]
  Grammar masking is used to guide large language models toward producing syntactically correct models for a given context-free grammar. We show that grammar masking can dramatically improve the modeling capabilities of several language models.
  arXiv  Detail & Related papers  (2024-07-08T17:19:59Z)
• How Ready Are Generative Pre-trained Large Language Models for Explaining Bengali Grammatical Errors? [0.4857223913212445]
  Grammatical error correction (GEC) tools, powered by advanced generative artificial intelligence (AI), competently correct linguistic inaccuracies in user input. However, they often fall short in providing essential natural language explanations. In such languages, grammatical error explanation (GEE) systems should not only correct sentences but also provide explanations for errors.
  arXiv  Detail & Related papers  (2024-05-27T15:56:45Z)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  We propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to fill the gap between programming languages and natural language. Various experiments and ablations are done on four datasets including both the C++ and python languages to validate the hard meta-graph prompt, the soft prompting technique, and the effectiveness of the objectives for pretrained GNN expert.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)
• Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning [27.59524153097858]
  grammar-constrained decoding (GCD) can be used to control the generation of large language models (LMs) GCD can serve as a unified framework for structured NLP tasks in general. We show that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models.
  arXiv  Detail & Related papers  (2023-05-23T11:54:37Z)
• GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator [114.8954615026781]
  We propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator. GanLM is trained with two pre-training objectives: replaced token detection and replaced token denoising. Experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models.
  arXiv  Detail & Related papers  (2022-12-20T12:51:11Z)
• CLSE: Corpus of Linguistically Significant Entities [58.29901964387952]
  We release a Corpus of Linguistically Significant Entities (CLSE) annotated by experts. CLSE covers 74 different semantic types to support various applications from airline ticketing to video games. We create a linguistically representative NLG evaluation benchmark in three languages: French, Marathi, and Russian.
  arXiv  Detail & Related papers  (2022-11-04T12:56:12Z)
• Benchmarking Language Models for Code Syntax Understanding [79.11525961219591]
  Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding. In this work, we perform the first thorough benchmarking of the state-of-the-art pre-trained models for identifying the syntactic structures of programs. Our findings point out key limitations of existing pre-training methods for programming languages, and suggest the importance of modeling code syntactic structures.
  arXiv  Detail & Related papers  (2022-10-26T04:47:18Z)
• ContraCLM: Contrastive Learning For Causal Language Model [54.828635613501376]
  We present ContraCLM, a novel contrastive learning framework at both token-level and sequence-level. We show that ContraCLM enhances discrimination of the representations and bridges the gap with the encoder-only models.
  arXiv  Detail & Related papers  (2022-10-03T18:56:35Z)
• Learning grammar with a divide-and-concur neural network [4.111899441919164]
  We implement a divide-and-concur iterative projection approach to context-free grammar inference. Our method requires a relatively small number of discrete parameters, making the inferred grammar directly interpretable.
  arXiv  Detail & Related papers  (2022-01-18T22:42:43Z)
• On the Robustness of Language Encoders against Grammatical Errors [66.05648604987479]
  We collect real grammatical errors from non-native speakers and conduct adversarial attacks to simulate these errors on clean text data. Results confirm that the performance of all tested models is affected but the degree of impact varies.
  arXiv  Detail & Related papers  (2020-05-12T11:01:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.