Pith. sign in

REVIEW 9 cited by

Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.07989 v7 pith:AHGV3LSG submitted 2023-11-14 cs.CL cs.AIcs.SE

Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code

classification cs.CL cs.AIcs.SE
keywords modelslanguageengineeringcodesoftwareevaluationgithubllms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work we systematically review the recent advancements in software engineering with language models, covering 70+ models, 40+ evaluation tasks, 180+ datasets, and 900 related works. Unlike previous works, we integrate software engineering (SE) with natural language processing (NLP) by discussing the perspectives of both sides: SE applies language models for development automation, while NLP adopts SE tasks for language model evaluation. We break down code processing models into general language models represented by the GPT family and specialized models that are specifically pretrained on code, often with tailored objectives. We discuss the relations and differences between these models, and highlight the historical transition of code modeling from statistical models and RNNs to pretrained Transformers and LLMs, which is exactly the same course that had been taken by NLP. We also go beyond programming and review LLMs' application in other software engineering activities including requirement engineering, testing, deployment, and operations in an endeavor to provide a global view of NLP in SE, and identify key challenges and potential future directions in this domain. We keep the survey open and updated on GitHub at https://github.com/codefuse-ai/Awesome-Code-LLM.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates

    cs.SE 2026-04 unverdicted novelty 7.0

    RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than p...

  2. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

    cs.CL 2026-02 unverdicted novelty 7.0

    Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.

  3. OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research

    cs.SE 2025-04 accept novelty 7.0

    OpenClassGen supplies 324,843 real-world Python classes with self-contained skeletons and static metrics to support LLM class generation research and evaluation.

  4. AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code

    cs.CL 2026-05 unverdicted novelty 6.0

    AutoVecCoder combines VecPrompt for automated intrinsic knowledge synthesis and VecRL for efficiency-aligned RL to train an 8B LLM that achieves SOTA on SimdBench SSE/AVX subsets and sometimes exceeds -O3 compiler results.

  5. A Study of LLMs' Preferences for Libraries and Programming Languages

    cs.SE 2025-03 unverdicted novelty 6.0

    Empirical study of eight LLMs finds overuse of popular libraries like NumPy in up to 45% of unnecessary cases and strong default preference for Python even when suboptimal.

  6. CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs

    cs.SE 2025-02 unverdicted novelty 6.0

    CodePromptZip builds a code compressor via type-aware ablation-ranked training samples and a copy-augmented small LM, reporting 23.4-28.7% gains over baselines on three RAG coding tasks.

  7. Prompt Optimization for LLM Code Generation via Reinforcement Learning

    cs.SE 2026-05 unverdicted novelty 5.0

    A PPO agent with hybrid actions and test-driven rewards optimizes prompts for code LLMs, raising strict Pass@1 scores on MBPP+, HumanEval+, and APPS over prior methods.

  8. What makes a harness a harness: necessary and sufficient conditions for an agent harness

    cs.SE 2026-06 unverdicted novelty 4.0

    Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.

  9. An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models

    cs.SE 2026-04 unverdicted novelty 4.0

    Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.