Leandojo: Theorem proving with retrieval-augmented language models
Large language models (LLMs) have shown promise in proving formal theorems using proof
assistants such as Lean. However, existing methods are difficult to reproduce or build on …
assistants such as Lean. However, existing methods are difficult to reproduce or build on …
Toolqa: A dataset for llm question answering with external tools
Abstract Large Language Models (LLMs) have demonstrated impressive performance in
various NLP tasks, but they still suffer from challenges such as hallucination and weak …
various NLP tasks, but they still suffer from challenges such as hallucination and weak …
Open-world story generation with structured knowledge enhancement: A comprehensive survey
Storytelling and narrative are fundamental to human experience, intertwined with our social
and cultural engagement. As such, researchers have long attempted to create systems that …
and cultural engagement. As such, researchers have long attempted to create systems that …
Dense text retrieval based on pretrained language models: A survey
Text retrieval is a long-standing research topic on information seeking, where a system is
required to return relevant information resources to user's queries in natural language. From …
required to return relevant information resources to user's queries in natural language. From …
Inferfix: End-to-end program repair with llms
Software development life cycle is profoundly influenced by bugs; their introduction,
identification, and eventual resolution account for a significant portion of software …
identification, and eventual resolution account for a significant portion of software …
Repocoder: Repository-level code completion through iterative retrieval and generation
The task of repository-level code completion is to continue writing the unfinished code based
on a broader context of the repository. While for automated code completion tools, it is …
on a broader context of the repository. While for automated code completion tools, it is …
Crosscodeeval: A diverse and multilingual benchmark for cross-file code completion
Code completion models have made significant progress in recent years, yet current popular
evaluation datasets, such as HumanEval and MBPP, predominantly focus on code …
evaluation datasets, such as HumanEval and MBPP, predominantly focus on code …
Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
Pangu-coder2: Boosting large language models for code with ranking feedback
B Shen, J Zhang, T Chen, D Zan, B Geng, A Fu… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models for Code (Code LLM) are flourishing. New and powerful models
are released on a weekly basis, demonstrating remarkable performance on the code …
are released on a weekly basis, demonstrating remarkable performance on the code …
Skcoder: A sketch-based approach for automatic code generation
Recently, deep learning techniques have shown great success in automatic code
generation. Inspired by the code reuse, some researchers propose copy-based approaches …
generation. Inspired by the code reuse, some researchers propose copy-based approaches …