MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
hub
Large language models for code generation: A comprehensive survey of challenges, techniques, evaluation, and applications.arXiv preprint arXiv:2503.01245
14 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
14
Pith papers citing it
2
external citations · external index
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
MocklessTester generates mockless Java unit tests using context mining and multi-level constraint fixing, improving coverage and mutation scores over baselines on Defects4J and Deps4J.
MA-CoT prompting reduces security findings in LLM-generated code by 57.6% on a 200-task dataset and 94.5% on LLMSecEval across C, Java, and Python, outperforming vanilla, zero-shot, and standard CoT strategies.
VeriContest supplies 946 problems with specs, code, proofs, and tests to benchmark verifiable code generation in Rust/Verus, showing models reach 92% on code but only 5% end-to-end on full verifiable synthesis.
A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and merging methods on reasoning and generation benchmarks.
A rule-aware modular prompt framework enables LLMs to perform structured numeric reasoning on power grid data by separating rules from normalized deviations, improving anomaly detection consistency and reducing token use in IEEE 118-bus tests.
SiriusHelper deploys an LLM agent with intent routing, DeepSearch multi-hop retrieval, and automated SOP distillation to outperform alternatives and reduce ticket volume by 20.8% on Tencent's big data platform.
ACE introduces a solver-adversary loop where an LLM generates both candidate programs and adversarial tests, using execution outcomes for preference optimization to achieve 3-7% pass@1 gains on code benchmarks without ground-truth code.
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
Develops a conceptual distinction between human-cognitive and artificial-stochastic error architectures in code generation, drawing on Dennett, Rescher, and Floridi to explore implications for AI-human collaboration.
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future research directions with 18 subcategories.
citing papers explorer
-
MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
-
LLM-based Mockless Unit Test Generation for Java
MocklessTester generates mockless Java unit tests using context mining and multi-level constraint fixing, improving coverage and mutation scores over baselines on Defects4J and Deps4J.
-
Enhancing Reliability in LLM-Based Secure Code Generation
MA-CoT prompting reduces security findings in LLM-generated code by 57.6% on a 200-task dataset and 94.5% on LLMSecEval across C, Java, and Python, outperforming vanilla, zero-shot, and standard CoT strategies.
-
VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
VeriContest supplies 946 problems with specs, code, proofs, and tests to benchmark verifiable code generation in Rust/Verus, showing models reach 92% on code but only 5% end-to-end on full verifiable synthesis.
-
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
-
Token-Level LLM Collaboration via FusionRoute
FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and merging methods on reasoning and generation benchmarks.
-
A Rule-Aware Prompt Framework for Structured Numeric Reasoning in Cyber-Physical Systems
A rule-aware modular prompt framework enables LLMs to perform structured numeric reasoning on power grid data by separating rules from normalized deviations, improving anomaly detection consistency and reducing token use in IEEE 118-bus tests.
-
SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms
SiriusHelper deploys an LLM agent with intent routing, DeepSearch multi-hop retrieval, and automated SOP distillation to outperform alternatives and reduce ticket volume by 20.8% on Tencent's big data platform.
-
ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
ACE introduces a solver-adversary loop where an LLM generates both candidate programs and adversarial tests, using execution outcomes for preference optimization to achieve 3-7% pass@1 gains on code benchmarks without ground-truth code.
-
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
-
Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation
Develops a conceptual distinction between human-cognitive and artificial-stochastic error architectures in code generation, drawing on Dennett, Rescher, and Floridi to explore implications for AI-human collaboration.
-
Sustainable Code Generation Using Large Language Models: A Systematic Literature Review
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
-
LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future research directions with 18 subcategories.
- MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation