English
Related papers

Related papers: dafny-annotator: AI-Assisted Verification of Dafny…

200 papers

Deep Active Learning (DAL) aims to reduce labeling costs in neural-network training by prioritizing the most informative unlabeled samples for annotation. Beyond selecting which samples to label, several DAL approaches further enhance data…

Machine Learning · Computer Science 2025-12-17 Jonathan Spiegelman , Guy Amir , Guy Katz

Large Language Models (LLMs) demonstrate strong performance in real-world applications, yet existing open-source instruction datasets often concentrate on narrow domains, such as mathematics or coding, limiting generalization and widening…

Computation and Language · Computer Science 2025-06-16 Jijie Li , Li Du , Hanyu Zhao , Bo-wen Zhang , Liangdong Wang , Boyan Gao , Guang Liu , Yonghua Lin

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Computation and Language · Computer Science 2024-10-21 Mozhi Zhang , Pengyu Wang , Chenkun Tan , Mianqiu Huang , Dong Zhang , Yaqian Zhou , Xipeng Qiu

Large language models (LLMs) have demonstrated remarkable progress in code generation, but many existing benchmarks are approaching saturation and offer little guarantee on the trustworthiness of the generated programs. To improve…

Software Engineering · Computer Science 2025-10-08 Xun Deng , Sicheng Zhong , Barış Bayazıt , Andreas Veneris , Fan Long , Xujie Si

Large Language Models (LLMs) are increasingly used to annotate learning interactions, yet concerns about reliability limit their utility. We test whether verification-oriented orchestration-prompting models to check their own labels…

Artificial Intelligence · Computer Science 2026-01-29 Bakhtawar Ahtisham , Kirk Vanacore , Jinsook Lee , Zhuqian Zhou , Doug Pietrzak , Rene F. Kizilcec

Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language…

Artificial Intelligence · Computer Science 2025-10-09 Qi Guo , Jianing Wang , Jianfei Zhang , Deyang Kong , Xiangzhou Huang , Xiangyu Xi , Wei Wang , Jingang Wang , Xunliang Cai , Shikun Zhang , Wei Ye

Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI…

Large Language Models (LLMs) have emerged as powerful support tools across various natural language tasks and a range of application domains. Recent studies focus on exploring their capabilities for data annotation. This paper provides a…

Computation and Language · Computer Science 2025-07-01 Maja Pavlovic , Massimo Poesio

Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other domains. Yet, deploying LLM-driven planning in the physical world demands strict adherence to…

Robotics · Computer Science 2026-05-27 Yunhao Yang , Junyuan Hong , Gabriel Jacob Perin , Zhiwen Fan , Li Yin , Zhangyang Wang , Ufuk Topcu

We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system. Adding more annotated training data for any ML system typically improves accuracy, but only if it…

Machine Learning · Computer Science 2019-09-02 Xi C. Chen , Adithya Sagar , Justine T. Kao , Tony Y. Li , Christopher Klein , Stephen Pulman , Ashish Garg , Jason D. Williams

Identifiers, such as method and variable names, form a large portion of source code. Therefore, low-quality identifiers can substantially hinder code comprehension. To support developers in using meaningful identifiers, several…

Software Engineering · Computer Science 2022-12-13 Antonio Mastropaolo , Emad Aghajani , Luca Pascarella , Gabriele Bavota

Proving equivalence between functional programs is a fundamental problem in program verification, which often amounts to reasoning about algebraic data types (ADTs) and compositions of structural recursions. Modern theorem provers address…

Programming Languages · Computer Science 2024-05-21 Yican Sun , Ruyi Ji , Jian Fang , Xuanlin Jiang , Mingshuai Chen , Yingfei Xiong

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder…

Computation and Language · Computer Science 2025-02-10 Zhaoyang Wang , Jinqi Jiang , Huichi Zhou , Wenhao Zheng , Xuchao Zhang , Chetan Bansal , Huaxiu Yao

The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models. However, datasets often contain noisy data inadvertently included during the construction process. Numerous attempts have been…

Computation and Language · Computer Science 2024-09-25 Juhwan Choi , Jungmin Yun , Kyohoon Jin , YoungBin Kim

Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human…

Machine Learning · Computer Science 2023-12-05 Zhiqing Sun , Yikang Shen , Qinhong Zhou , Hongxin Zhang , Zhenfang Chen , David Cox , Yiming Yang , Chuang Gan

Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to…

Computation and Language · Computer Science 2024-02-29 Hannah Kim , Kushan Mitra , Rafael Li Chen , Sajjadur Rahman , Dan Zhang

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…

Computation and Language · Computer Science 2024-06-19 Jie Chen , Yupeng Zhang , Bingning Wang , Wayne Xin Zhao , Ji-Rong Wen , Weipeng Chen

Background: Manual testing is vital for detecting issues missed by automated tests, but specifying accurate verifications is challenging. Aims: This study aims to explore the use of Large Language Models (LLMs) to produce verifications for…

Dafny is a verification-aware programming language that allows developers to formally specify their programs and prove them correct. Currently, a Dafny program is compiled in two steps: First, a backend translates the input program to a…

Programming Languages · Computer Science 2025-01-10 Daniel Nezamabadi , Magnus Myreen

Recent approaches to large language model (LLM) alignment typically require millions of human annotations or rely on external aligned models for synthetic data generation. This paper introduces ALMA: Alignment with Minimal Annotation,…

Computation and Language · Computer Science 2024-12-06 Michihiro Yasunaga , Leonid Shamis , Chunting Zhou , Andrew Cohen , Jason Weston , Luke Zettlemoyer , Marjan Ghazvininejad