REVIEW 8 cited by
Unified Pre-training for Program Understanding and Generation
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
read the original abstract
Code summarization and generation empower conversion between programming language (PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks, e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART's effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus excels even with limited annotations.
Forward citations
Cited by 8 Pith papers
-
Programmers Are Poor and Overconfident Judges of LLM-Generated Assertions
Developers are nearly three times more likely to correctly accept correct LLM assertions than to reject incorrect ones, and accompanying natural-language comments provide no net benefit and can increase overconfidence.
-
LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks
Across 83 SE benchmarks, average leakage into StarCoder's pretraining data is 4.8% (Python), 2.8% (Java), and 0.7% (C/C++), but QuixBugs and BigCloneBench are 100% and 55.7% leaked.
-
Quantize with Confidence? An Empirical Study of Quantization for Code Generation
4-bit quantization of code LLMs mostly preserves pass@1, but AQLM matches or beats full precision while QuIP# degrades most on complex prompts; sensitivity is model-dependent.
-
Automated Repair of C Programs Using Large Language Models
An agent that combines spectrum-based fault localization, test feedback, and chain-of-thought prompting repairs 44.93% of 3,902 Codeflaws C bugs, a 3.61-point gain over GPT-4 with CoT.
-
Metamorphic Testing of Deep Code Models: A Systematic Literature Review
A systematic review of 45 papers shows metamorphic testing of code models relies mostly on identifier renaming and dead code insertion, targets encoder-only models like CodeBERT, and under-covers generative tasks, new...
-
It Only Gets Worse: Revisiting DL-Based Vulnerability Detectors from a Practical Perspective
An evaluation of seven deep learning vulnerability detectors shows low consistency and poor generalization, and finds that code features beyond CWE labels strongly influence detection results.
-
VulBinLLM: LLM-powered Vulnerability Detection for Stripped Binaries
An LLM pipeline that enriches decompiled code with vulnerability hints and then classifies CWEs reports high Juliet accuracy, but leaky hints and unmatched baselines weaken the claim.
-
LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights
A survey of LLM-based vulnerability detection covering 58 papers, with a taxonomy, dataset overview, and gap analysis, but limited by non-transparent selection and unsupported quantitative claims.
Discussion (0). Continue with ORCID to comment.