CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.
arXiv preprint arXiv:2305.02309 , year=
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
polarities
background 4representative citing papers
The researchers provide a systematic 4-tier classification of 646 programming languages, quantifying the extreme data scarcity facing over 70% of the world's programming languages in the age of LLMs.
ChatHLS presents a multi-agent LLM system for HLS error debugging via adaptive case expansion and QoR-aware directive optimization, reporting 32.6% better debugging than Gemini-3-pro plus speedups on kernels and accelerators.
A 1.3B-parameter code model trained on 7B tokens of curated textbook and synthetic data achieves 50.6% on HumanEval, indicating data quality can enable strong performance at small scale.
Gorilla is a fine-tuned LLM that surpasses GPT-4 in accurate API call generation and uses retrieval to handle documentation updates.
PairCoder is a two-agent pair-programming method that leverages toolchain verification oracles to improve LLM generation of verifiable structured artifacts on 17 benchmarks across seven models.
VerilogCL applies contrastive learning with minimal-error data pairs and a proactive screening module to improve compilation success and functional correctness of 7B LLM-generated Verilog over open-source and commercial baselines on VerilogEval and RTLLM benchmarks.
A router mixes supervised and reward fine-tuning with compiler/security feedback so small code LLMs produce more functionally correct and security-cleared vulnerability patches on three repair benchmarks.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
citing papers explorer
-
Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.
-
A Taxonomy of Programming Languages for Code Generation
The researchers provide a systematic 4-tier classification of 646 programming languages, quantifying the extreme data scarcity facing over 70% of the world's programming languages in the age of LLMs.
-
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis
ChatHLS presents a multi-agent LLM system for HLS error debugging via adaptive case expansion and QoR-aware directive optimization, reporting 32.6% better debugging than Gemini-3-pro plus speedups on kernels and accelerators.
-
Textbooks Are All You Need
A 1.3B-parameter code model trained on 7B tokens of curated textbook and synthetic data achieves 50.6% on HumanEval, indicating data quality can enable strong performance at small scale.
-
Gorilla: Large Language Model Connected with Massive APIs
Gorilla is a fine-tuned LLM that surpasses GPT-4 in accurate API call generation and uses retrieval to handle documentation updates.
-
PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation
PairCoder is a two-agent pair-programming method that leverages toolchain verification oracles to improve LLM generation of verifiable structured artifacts on 17 benchmarks across seven models.
-
VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation
VerilogCL applies contrastive learning with minimal-error data pairs and a proactive screening module to improve compilation success and functional correctness of 7B LLM-generated Verilog over open-source and commercial baselines on VerilogEval and RTLLM benchmarks.
-
SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
A router mixes supervised and reward fine-tuning with compiler/security feedback so small code LLMs produce more functionally correct and security-cleared vulnerability patches on three repair benchmarks.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
-
Context-Guided Decompilation: A Step Towards Re-executability
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
-
A Survey of Large Language Models
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.