Pith. sign in

REVIEW 12 cited by

Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2403.07506 v1 pith:2O6RJBE2 submitted 2024-03-12 cs.SE

Zhou Yang , Zhensu Sun , Terry Zhuo Yue , Premkumar Devanbu , David Lo This is my paper · ORCID
classification cs.SE
keywords codepropertiesaccuracyefficiencyexplainabilityidentifylanguagelarge
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models for code (LLM4Code), which demonstrate strong performance (e.g., high accuracy) in processing source code, have significantly transformed software engineering. Many studies separately investigate the non-functional properties of LM4Code, but there is no systematic review of how these properties are evaluated and enhanced. This paper fills this gap by thoroughly examining 146 relevant studies, thereby presenting the first systematic literature review to identify seven important properties beyond accuracy, including robustness, security, privacy, explainability, efficiency, and usability. We discuss the current state-of-the-art methods and trends, identify gaps in existing research, and present promising directions for future study.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation

    cs.CR 2026-07 conditional novelty 7.0 of 10

    Injected insecure coding preferences in LLM long-term memory raise vulnerability rates by 2.7-50.3 pp and suppress warnings; memory-level filtering restores safe behavior in the tested set.

  2. Unified Communication Compression Beyond Global Error Bounds for Distributed Nonconvex Optimization

    math.OC 2026-04 unverdicted novelty 7.0 of 10

    A unified compression algorithm for distributed nonconvex optimization achieves O(1/sqrt(T)) convergence for locally-bounded compressors, matching centralized 1-bit methods, with an improved O(1/T^{2/3}) rate after on...

  3. Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?

    cs.CV 2025-01 conditional novelty 7.0 of 10

    Standard gender-bias detectors for text-to-image models deviate substantially from human-annotated bias, and a face-filtering plus CLIP pipeline measures bias more accurately.

  4. Symbol and Footprint Database for Electronic Components by Agentic Recognition and Generation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    An MLLM-driven agentic pipeline generates PCB component symbols and footprints from datasheets with reported 86%/80% accuracy and builds a 1,000-component library.

  5. "My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    Using 1,085 marketplace extensions and reviews of 32 assistants, this study maps developer satisfaction and criticism into a taxonomy and five design implications.

  6. Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation

    cs.SE 2025-06 reject novelty 5.0 of 10

    Quantized code LLMs appear more robust than full-precision ones in a majority of tested adversarial and noise scenarios, but the proposed Relative Robustness Score is misspecified.

  7. Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities

    cs.SE 2025-05 conditional novelty 5.0 of 10

    Commercial LLMs deobfuscate simple OLLVM-obfuscated assembly well for some techniques but universally fail when three obfuscations are combined.

  8. CodeImprove: Program Adaptation for Deep Code Models

    cs.SE 2025-01 conditional novelty 5.0 of 10

    Adapting program inputs with a layerwise validity score and genetic search improves deep code model accuracy by up to 8.78% without retraining.

  9. An Empirical Study of Vulnerable Package Dependencies in LLM Repositories

    cs.CR 2025-08 conditional novelty 4.0 of 10

    In 52 open-source LLM projects, 75.8% of those with dependency configs use at least one vulnerable package, and half of supply chain vulnerabilities stay undisclosed for over 56 months.

  10. A Functional Software Reference Architecture for LLM-Integrated Systems

    cs.SE 2025-01 conditional novelty 4.0 of 10

    A preliminary four-layer functional reference architecture for LLM-integrated systems, illustrated on three open-source projects.

  11. Towards Advancing Code Generation with Large Language Models: A Research Roadmap

    cs.SE 2025-01 conditional novelty 4.0 of 10

    A roadmap paper that organizes LLM code generation into a six-layer architecture and a four-phase human-in-the-loop workflow, and lists open challenges and recommendations.

  12. Position Paper: Programming Language Techniques for Bridging LLM Code Generation Semantic Gaps

    cs.SE 2025-07 unverdicted novelty 2.0 of 10

    A position paper arguing that PL techniques, especially formal verification and structure-aware representations, should be deeply integrated into LLM code generation.

Pith tools