paper-with-me

홈 › Papers

Coder Reviewer Reranking for Code Generation

2022-11-29 · Tianyi Zhang, Tao Yu, Tatsunori B. Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I. Wang

Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions. Inspired by collaborative programming, we propose Coder-Reviewer reranking. We augment Coder language models from past work, which generate programs given language instructions, with Reviewer models, which evaluate the likelihood of the instruction given the generated programs. We perform an extensive study across six datasets with eight models from three model families. Experimental results show that Coder-Reviewer reranking leads to consistent and significant improvement (up to 17% absolute accuracy gain) over reranking with the Coder model only. When combined with executability filtering, Coder-Reviewer reranking can often outperform the minimum Bayes risk method. Coder-Reviewer reranking is easy to implement by prompting, can generalize to different programming languages, and works well with off-the-shelf hyperparameters.

📄 PDF Abstract BibTeX arXiv:2211.16490

Code (1)

facebookresearch/coder_reviewer_reranking 공식 구현 pytorch

Tasks

Code GenerationLanguage ModelingLanguage ModellingReranking

Similar Papers 제목 키워드 기반

Functional Overlap Reranking for Neural Code Generation

2023-10-16 · Hung Quoc To, Minh Huynh Nguyen, Nghi D. Q. Bui

Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often ov…

Code GenerationReranking

Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models

2023-12-26 · Manveer Singh Tamber, Ronak Pradeep, Jimmy Lin

Recent work in zero-shot listwise reranking using LLMs has achieved state-of-the-art results. However, these methods are not without drawbacks. The proposed methods rely on large LLMs with billions of parameters and limi…

DecoderReranking

Pragmatic Reasoning improves LLM Code Generation

2025-02-20 · Zhuchen Cao, Sven Apel, Adish Singla, Vera Demberg

Large Language Models (LLMs) have demonstrated impressive potential in translating natural language (NL) instructions into program code. However, user instructions often contain inherent ambiguities, making it challengin…

Code GenerationReranking

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation

2024-02-05 · Shicheng Xu, Liang Pang, Jun Xu, HuaWei Shen 외

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List…

Information RetrievalLearning-To-RankMisinformationReranking+2

Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis

2026-02-18 · Zhiyuan Cheng, Longying Lai, Yue Liu, Kai Cheng 외 arxiv

Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a Retrieval-Augmented Generation (RAG) system designed to answer question…

Semantic Retrieval