paper-with-me

Papers

Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration

2025-03-10 · Zhao Jin, Lu Jin, Yizhe Luo, Shuo Feng, Yucheng Shi, Kai Zheng, Xinde Yu, Mingliang Xu

Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization.

📄 PDF Abstract BibTeX arXiv:2503.07096

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Deductive Verification of Chain-of-Thought Reasoning

2023-06-06 · NeurIPS 2023 11 · Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang 외

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on i…

Logical Reasoning

Next Steps in LLM-Supported Java Verification

2025-02-03 · Samuel Teuber, Bernhard Beckert

Recent work has shown that Large Language Models (LLMs) are not only a suitable tool for code generation but also capable of generating annotation-based code specifications. Scaling these methodologies may allow us to de…

Code Generation

AutoVerus: Automated Proof Generation for Rust Code

2024-09-19 · Chenyuan Yang, Xuheng Li, Md Rakib Hossain Misu, Jianan Yao 외

Generative AI has shown its values for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. …

Code GenerationLanguage ModelingLanguage ModellingLarge Language Model

Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability

2024-01-16 · Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen, Derry Wijaya 외

While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world. As a consequen…

Fact VerificationText Generation

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

2025-05-07 · Qi Liu, Xinhao Zheng, Renqiu Xia, Xingzhi Qi 외

As a seemingly self-explanatory task, problem-solving has been a significant component of science and engineering. However, a general yet concrete formulation of problem-solving itself is missing. With the recent develop…

Automated Theorem Proving