English
Related papers

Related papers: Training Language Models on Synthetic Edit Sequenc…

200 papers

Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in…

Computation and Language · Computer Science 2023-04-18 Swapnil Sharma , Nikita Anand , Kranthi Kiran G.

A key challenge in program synthesis is the astronomical size of the search space the synthesizer has to explore. In response to this challenge, recent work proposed to guide synthesis using learned probabilistic models. Obtaining such a…

Programming Languages · Computer Science 2020-10-20 Shraddha Barke , Hila Peleg , Nadia Polikarpova

Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a closed-loop…

Machine Learning · Computer Science 2026-04-17 Waleed Khalid , Dmitry Ignatov , Radu Timofte

This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to…

Computation and Language · Computer Science 2024-10-08 Houcheng Jiang , Junfeng Fang , Tianyu Zhang , An Zhang , Ruipeng Wang , Tao Liang , Xiang Wang

Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…

As the demand for high-quality data in model training grows, researchers and developers are increasingly generating synthetic data to tune and train LLMs. However, current data generation methods rely on seed sets containing tens of…

Computation and Language · Computer Science 2025-05-22 Alan Zhu , Parth Asawa , Jared Quincy Davis , Lingjiao Chen , Boris Hanin , Ion Stoica , Joseph E. Gonzalez , Matei Zaharia

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Large language models (LLMs) have demonstrated strong capabilities in generating executable code from natural language descriptions. However, general-purpose models often struggle in specialized programming contexts where domain-specific…

Artificial Intelligence · Computer Science 2026-03-18 Luís Freire , Fernanda A. Andaló , Nicki Skafte Detlefsen

Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible…

Software Engineering · Computer Science 2025-03-25 Xue Jiang , Yihong Dong , Yongding Tao , Huanyu Liu , Zhi Jin , Wenpin Jiao , Ge Li

Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is constrained by the scarcity of high-quality, publicly…

Software Engineering · Computer Science 2025-08-11 Wasi Uddin Ahmad , Aleksander Ficek , Mehrzad Samadi , Jocelyn Huang , Vahid Noroozi , Somshubra Majumdar , Boris Ginsburg

The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select…

Computation and Language · Computer Science 2022-11-24 Bei Chen , Fengji Zhang , Anh Nguyen , Daoguang Zan , Zeqi Lin , Jian-Guang Lou , Weizhu Chen

Software analytics often builds from labeled data. Labeling can be slow, error prone, and expensive. When human expertise is scarce, SE researchers sometimes ask large language models (LLMs) for the missing labels. While this has been…

Software Engineering · Computer Science 2026-03-25 Lohith Senthilkumar , Tim Menzies

The increasing use of synthetic data generated by Large Language Models (LLMs) presents both opportunities and challenges in data-driven applications. While synthetic data provides a cost-effective, scalable alternative to real-world data…

Computation and Language · Computer Science 2025-07-25 Tevin Atwal , Chan Nam Tieu , Yefeng Yuan , Zhan Shi , Yuhong Liu , Liang Cheng

Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not…

Computation and Language · Computer Science 2021-09-07 Inbar Oren , Jonathan Herzig , Jonathan Berant

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Computation and Language · Computer Science 2026-01-30 Ajay Patel , Colin Raffel , Chris Callison-Burch

High-quality labeled datasets are fundamental for training and evaluating machine learning models, yet domains such as healthcare and Requirements Engineering (RE) face persistent barriers due to data scarcity, privacy constraints, or…

Software Engineering · Computer Science 2026-03-31 Abdelkarim El-Hajjami , Camille Salinesi

Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural…

Programming Languages · Computer Science 2025-08-11 Anjiang Wei , Tarun Suresh , Jiannan Cao , Naveen Kannan , Yuheng Wu , Kai Yan , Thiago S. F. X. Teixeira , Ke Wang , Alex Aiken

Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edits directly can be challenging due to the scarcity of rich…

Artificial Intelligence · Computer Science 2024-06-03 Shreyas Kapur , Erik Jenner , Stuart Russell

In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100…

Computation and Language · Computer Science 2023-08-15 Xueying Du , Mingwei Liu , Kaixin Wang , Hanlin Wang , Junwei Liu , Yixuan Chen , Jiayi Feng , Chaofeng Sha , Xin Peng , Yiling Lou

This study investigates the reliability of code generation by Large Language Models (LLMs), focusing on identifying and analyzing defects in the generated code. Despite the advanced capabilities of LLMs in automating code generation,…

Software Engineering · Computer Science 2024-08-27 Ali Mohammadi Esfahani , Nafiseh Kahani , Samuel A. Ajila