English
Related papers

Related papers: Lyra: A Benchmark for Turducken-Style Code Generat…

200 papers

Large, human-annotated datasets are central to the development of natural language processing models. Collecting these datasets can be the most challenging part of the development process. We address this problem by introducing a general…

Computation and Language · Computer Science 2020-04-29 Alana Marzoev , Samuel Madden , M. Frans Kaashoek , Michael Cafarella , Jacob Andreas

Statistical language modeling techniques have successfully been applied to source code, yielding a variety of new software development tools, such as tools for code suggestion and improving readability. A major issue with these techniques…

Software Engineering · Computer Science 2019-03-15 Rafael-Michael Karampatsis , Charles Sutton

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward…

Computation and Language · Computer Science 2023-10-13 Xi Ye , Qiaochu Chen , Isil Dillig , Greg Durrett

Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…

Software Engineering · Computer Science 2020-08-19 Aditya Kanade , Petros Maniatis , Gogul Balakrishnan , Kensen Shi

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Computation and Language · Computer Science 2025-05-30 Yongchao Chen , Yilun Hao , Yueying Liu , Yang Zhang , Chuchu Fan

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Machine Learning · Computer Science 2025-05-09 Niels Mündler , Jingxuan He , Hao Wang , Koushik Sen , Dawn Song , Martin Vechev

Linear Temporal Logic (LTL) is a widely used task specification language for autonomous systems. To mitigate the significant manual effort and expertise required to define LTL-encoded tasks, several methods have been proposed for…

Computation and Language · Computer Science 2026-02-23 David Smith Sundarsingh , Jun Wang , Jyotirmoy V. Deshmukh , Yiannis Kantaros

Large Language Models (LLMs), such as ChatGPT, are increasingly leveraged for generating both traditional software code and spreadsheet logic. Despite their impressive generative capabilities, these models frequently exhibit critical issues…

Software Engineering · Computer Science 2025-11-27 Simon Thorne , Advait Sarkar

Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and counterfactual alternatives. Similar challenges arise in natural language-to-code generation, where…

Computation and Language · Computer Science 2026-05-26 Zhuchen Cao , Sven Apel , Adish Singla , Vera Demberg

The text-to-SQL task is an active challenge in Natural Language Processing. Many existing solutions focus on using black-box language models extended with specialized components within customized end-to-end text-to-SQL pipelines. While…

Machine Learning · Computer Science 2025-11-17 Alicja Rączkowska , Riccardo Belluzzo , Piotr Zieliński , Joanna Baran , Paweł Olszewski

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Computation and Language · Computer Science 2025-11-25 Alfredo Garrachón Ruiz , Tomás de la Rosa , Daniel Borrajo

Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the generation. \citet{chen2020logic2text} have addressed this…

Computation and Language · Computer Science 2021-12-14 Ao Liu , Congjian Luo , Naoaki Okazaki

Library learning is the process of building a library of common functionalities from a given set of programs. Typically, this process is applied in the context of aiding program synthesis: concise functions can help the synthesizer produce…

Programming Languages · Computer Science 2024-10-10 Abhiram Bellur , Razan Alghamdi , Kidus Workneh , Joseph Izraelevitz

Many real-world software tasks require exact transcription of provided data into code, such as cryptographic constants, protocol test vectors, allowlists, and calibration tables. These tasks are operationally sensitive because small…

Software Engineering · Computer Science 2026-01-08 Mohd Ariful Haque , Kishor Datta Gupta , Mohammad Ashiqur Rahman , Roy George

Parsing is a fundamental building block in modern compilers, and for industrial programming languages, it is a surprisingly involved task. There are known approaches to generate parsers automatically, but the prevailing consensus is that…

Formal Languages and Automata Theory · Computer Science 2022-09-20 Joe Zimmerman

Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform…

Software Engineering · Computer Science 2024-11-18 Md. Asif Haider , Ayesha Binte Mostofa , Sk. Sabit Bin Mosaddek , Anindya Iqbal , Toufique Ahmed

We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a…

Computation and Language · Computer Science 2025-03-03 Jędrzej Warczyński , Mateusz Lango , Ondrej Dusek

Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by externally rejecting…

Programming Languages · Computer Science 2026-02-09 Zhechong Huang , Zhao Zhang , Ruyi Ji , Tingxuan Xia , Qihao Zhu , Qinxiang Cao , Zeyu Sun , Wiggin Zhou , Yingfei Xiong

Large language models have made significant progress in various language tasks, yet they still struggle with complex mathematics. In this paper, we propose ToRA a series of Tool-integrated Reasoning Agents designed to solve challenging…

Computation and Language · Computer Science 2024-02-22 Zhibin Gou , Zhihong Shao , Yeyun Gong , Yelong Shen , Yujiu Yang , Minlie Huang , Nan Duan , Weizhu Chen

Quantitative reasoning is a critical skill to analyze data, yet the assessment of such ability remains limited. To address this gap, we introduce the Quantitative Reasoning with Data (QRData) benchmark, aiming to evaluate Large Language…

Computation and Language · Computer Science 2024-06-11 Xiao Liu , Zirui Wu , Xueqing Wu , Pan Lu , Kai-Wei Chang , Yansong Feng