paper-with-me

Papers

Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning

2024-07-06 · Yun-Da Tsai, Mingjie Liu, Haoxing Ren

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning methods aimed at enhancing the efficiency of model training specifically for code LLMs. We present techniques that integrate various clustering and pruning metrics to selectively reduce training data without compromising the accuracy and functionality of the generated code. We observe significant redundancies in synthetic training data generation, where our experiments demonstrate that benchmark performance can be largely preserved by training on only 10% of the data. Moreover, we observe consistent improvements in benchmark results through moderate pruning of the training data. Our experiments show that these pruning strategies not only reduce the computational resources needed but also enhance the overall quality code generation.

📄 PDF Abstract BibTeX arXiv:2407.05040

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition

2025-07-17 · Yufei Peng, Yonggang Zhang, Yiu-ming Cheung

The variance in class-wise sample sizes within long-tailed scenarios often results in degraded performance in less frequent classes. Fortunately, foundation models, pre-trained on vast open-world datasets, demonstrate st…

Overriding Safety protections of Open-source Models

2024-09-28 · Sachin Kumar

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial a…

Red TeamingSafety Alignment

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

2025-08-24 · Mia Taylor, James Chua, Jan Betley, Johannes Treutlein 외 arxiv

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents …

$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs

2024-11-26 · Selim Furkan Tekin, Fatih Ilhan, Tiansheng Huang, Sihao Hu 외

Alignment of pretrained LLMs using instruction-based datasets is critical for creating fine-tuned models that reflect human preference. A growing number of alignment-based fine-tuning algorithms and benchmarks emerged re…

Mixture-of-Experts

Aligning the Pretraining and Finetuning Objectives of Language Models

2020-02-05 · Nuo Wang Pierse, Jingwen Lu

We demonstrate that explicitly aligning the pretraining objectives to the finetuning objectives in language model training significantly improves the finetuning task performance and reduces the minimum amount of finetuni…

Language ModelingLanguage Modelling