paper-with-me

Papers

Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation

2024-05-30 · Jingchang Chen, Hongxuan Tang, Zheng Chu, Qianglong Chen, Zekun Wang, Ming Liu, Bing Qin

Despite recent progress made by large language models in code generation, they still struggle with programs that meet complex requirements. Recent work utilizes plan-and-solve decomposition to decrease the complexity and leverage self-tests to refine the generated program. Yet, planning deep-inside requirements in advance can be challenging, and the tests need to be accurate to accomplish self-improvement. To this end, we propose FunCoder, a code generation framework incorporating the divide-and-conquer strategy with functional consensus. Specifically, FunCoder recursively branches off sub-functions as smaller goals during code generation, represented by a tree hierarchy. These sub-functions are then composited to attain more complex objectives. Additionally, we designate functions via a consensus formed by identifying similarities in program behavior, mitigating error propagation. FunCoder outperforms state-of-the-art methods by +9.8% on average in HumanEval, MBPP, xCodeEval and MATH with GPT-3.5 and GPT-4. Moreover, our method demonstrates superiority on smaller models: With FunCoder, StableCode-3b surpasses GPT-3.5 by +18.6% and achieves 97.7% of GPT-4's performance on HumanEval. Further analysis reveals that our proposed dynamic function decomposition is capable of handling complex requirements, and the functional consensus prevails over self-testing in correctness evaluation.

📄 PDF Abstract BibTeX arXiv:2405.20092

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationHumanEvalMathmbpp

Methods 이 논문이 사용한 방법론

15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data

2018-07-01 · ICML 2018 7 · Ganggang Xu, Zuofeng Shang, Guang Cheng

Divide-and-conquer is a powerful approach for large and massive data analysis. In the nonparameteric regression setting, although various theoretical frameworks have been established to achieve optimality in estimat…

regressionTwo-sample testing

Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model

2026-08-04 · Yufei Wu, Shanqing Gao, Andreas Voss, Francis Tuerlinckx arxiv

The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research. Although numerous estimation methods exist, researchers continue to seek inference approaches that are both fast and flexible across…

Bayesian Inference

An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models

2024-02-08 · Yizhou Zhang, Lun Du, Defu Cao, Qiang Fu 외

Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. However, when handling tasks involving repetitive sub-tasks and/or decepti…

Fact VerificationFake News DetectionHallucinationMisinformation

A Parallel Divide-and-Conquer based Evolutionary Algorithm for Large-scale Optimization

2018-12-06 · Peng Yang, Ke Tang, Xin Yao

Large-scale optimization problems that involve thousands of decision variables have extensively arisen from various industrial areas. As a powerful optimization tool for many real-world applications, evolutionary algorit…

Evolutionary Algorithms

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

2022-04-21 · Chunbo Lang, Binfei Tu, Gong Cheng, Junwei Han

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype …

DecoderFew-Shot Semantic SegmentationMeta-LearningSegmentation+1