Related papers: ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge

Related papers

PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems [0.0]
This article proposes PARCER as an engineering response to these limitations.<n>The framework acts as a declarative "operational contract" in YAML, transforming interactions into versioned and executable artifacts.<n>The objective of this work is to present the conceptual and technical architecture of PARCER, positioning it as a necessary transition from simple "prompt engineering" to "context engineering with governable governance"
arXiv Detail & Related papers (2026-03-01T01:11:53Z)
LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
arXiv Detail & Related papers (2026-01-31T10:18:32Z)
Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
arXiv Detail & Related papers (2025-12-26T07:53:41Z)
MedDCR: Learning to Design Agentic Workflows for Medical Coding [55.51674334874892]
Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes.<n>We present MedDCR, a closed-loop framework that treats design as a learning problem.<n>On benchmark datasets, MedDCR outperforms state-of-the-art baselines.
arXiv Detail & Related papers (2025-11-17T13:30:51Z)
Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning [65.20602712957725]
Caco is a novel framework that automates the synthesis of high-quality, verifiable, and diverse instruction-CoT reasoning data.<n>Our work establishes a paradigm for building self-sustaining, trustworthy reasoning systems without human intervention.
arXiv Detail & Related papers (2025-10-05T07:59:24Z)
Automatic Building Code Review: A Case Study [6.530899637501737]
Building officials face labor-intensive, error-prone, and costly manual reviews of design documents as projects increase in size and complexity.<n>This study introduces a novel agent-driven framework that integrates BIM-based data extraction with automated verification.
arXiv Detail & Related papers (2025-10-03T00:30:14Z)
Automated Facility Enumeration for Building Compliance Checking using Door Detection and Large Language Models [35.359387547360434]
Building compliance checking (BCC) is a critical process for ensuring that constructed facilities meet regulatory standards.<n>Despite its importance, this problem has been largely overlooked in the literature.<n>Recent advances in large language models (LLMs) offer new opportunities to enhance automation.
arXiv Detail & Related papers (2025-09-21T23:41:44Z)
Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification [46.845133190560375]
Motivated by how humans use systematic checklists to efficiently debug complex code, we propose textbfRePro, a textbfReflective Paper-to-Code textbfReproduction framework.<n>It automatically extracts a paper's fingerprint, referring to a comprehensive set of accurate and atomic criteria serving as high-quality supervisory signals.<n>It achieves 13.0% performance gap over baselines, and it correctly revises complex logical and mathematical criteria in reflecting.
arXiv Detail & Related papers (2025-08-21T06:57:44Z)
Explainability as a Compliance Requirement: What Regulated Industries Need from AI Tools for Design Artifact Generation [0.7874708385247352]
We investigate the explainability gap in AI-driven design artifact generation through semistructured interviews with ten practitioners from safety-critical industries.<n>Our findings reveal that non-explainable AI outputs necessitate extensive manual validation, reduce stakeholder trust, struggle to handle domain-specific terminology, disrupt team collaboration, and introduce regulatory compliance risks.<n>This study outlines a practical roadmap for improving the transparency, reliability, and applicability of AI tools in requirements engineering.
arXiv Detail & Related papers (2025-07-12T09:34:39Z)
An AST-guided LLM Approach for SVRF Code Synthesis [0.0]
This paper introduces a novel methodology integrating Abstract Syntax Tree (AST) embedding and Retrieval-Augmented Generation (RAG) for enhanced SVRF code synthesis.<n>We demonstrate up to a 40% improvement in code generation accuracy compared to basic text-based fine-tuning process.
arXiv Detail & Related papers (2025-07-01T00:57:45Z)
Large Language Model-Driven Code Compliance Checking in Building Information Modeling [3.2648052741820166]
This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling.<n>It introduces a Large Language Model (LLM)-driven approach to semi-automate this critical process.<n>The developed system integrates LLMs such as GPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks.
arXiv Detail & Related papers (2025-06-25T15:50:34Z)
Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
arXiv Detail & Related papers (2025-05-28T17:57:47Z)
Evaluating Large Language Models for Real-World Engineering Tasks [75.97299249823972]
This paper introduces a curated database comprising over 100 questions derived from authentic, production-oriented engineering scenarios.<n>Using this dataset, we evaluate four state-of-the-art Large Language Models (LLMs)<n>Our results show that LLMs demonstrate strengths in basic temporal and structural reasoning but struggle significantly with abstract reasoning, formal modeling, and context-sensitive engineering logic.
arXiv Detail & Related papers (2025-05-12T14:05:23Z)
AlignRAG: An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG [61.28113271728859]
Retrieval-augmented generation (RAG) has emerged as a foundational paradigm for knowledge-grounded text generation. Existing RAG pipelines often fail to ensure that the reasoning trajectories align with the evidential constraints imposed by retrieved content. We propose AlignRAG, a novel test-time framework that mitigates reasoning misalignment through iterative Critique-Driven Alignment steps.
arXiv Detail & Related papers (2025-04-21T04:56:47Z)
Representing Normative Regulations in OWL DL for Automated Compliance Checking Supported by Text Annotation [0.138120109831448]
We propose an annotation schema and an algorithm that transforms text annotations into machine-interpretable OWL DL code. The proposed approach is validated through a proof-of-concept implementation applied to examples from the building construction domain.
arXiv Detail & Related papers (2025-04-08T12:05:21Z)
A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences [76.73731245899454]
We propose a transparent law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience.<n>Inspired by this schema, we introduce the challenging task, which takes a textual case description and outputs a hierarchical structure justifying the final decision.<n>This benchmark paves the way for transparent and accountable AI-assisted law reasoning in the Intelligent Court''
arXiv Detail & Related papers (2025-03-02T10:26:54Z)
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
arXiv Detail & Related papers (2025-02-20T13:50:02Z)
Learning Task Representations from In-Context Learning [73.72066284711462]
Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning.<n>We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads.<n>We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
arXiv Detail & Related papers (2025-02-08T00:16:44Z)
Enhancing Code Consistency in AI Research with Large Language Models and Retrieval-Augmented Generation [0.0]
This paper presents a novel system designed to verify code implementations against the algorithms and methodologies outlined in corresponding research papers.<n>Our system employs Retrieval-Augmented Generation to extract relevant details from both the research papers and code bases, followed by a structured comparison using Large Language Models.
arXiv Detail & Related papers (2025-02-02T00:35:42Z)
A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement [0.0]
Article proposes a novel framework combining expert systems with a knowledge-based architecture to improve the precision and contextual relevance of AI-driven legal services.<n>This framework utilizes specialized modules, each focusing on specific legal areas, and incorporates structured operational guidelines to enhance decision-making.<n>The proposed approach demonstrates significant improvements over existing AI models, showcasing enhanced performance in legal tasks and offering a scalable solution to provide more accessible and affordable legal services.
arXiv Detail & Related papers (2024-12-29T14:00:11Z)
Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
arXiv Detail & Related papers (2024-10-05T05:21:48Z)
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks [68.49251303172674]
State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and retrieval-augmented generation (RAG) to decompose a complex problem into simpler steps and apply retrieval to improve factual correctness. We introduce Critic-guided planning with Retrieval-augmentation, CR-Planner, a novel framework that leverages fine-tuned critic models to guide both reasoning and retrieval processes through planning.
arXiv Detail & Related papers (2024-10-02T11:26:02Z)
Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection [0.0]
We introduce a novel autonomous agent framework leveraging Retrieval-Augmented Instruction-Tuning (RAIT) to enhance open, customizable small code language models (SLMs) By combining instruction tuned code SLMs with Retrieval-Augmented Code Generation (RACG) using external tools, the agent generates, debugs, and optimize code from natural language specifications. Our approach addresses the limitations of the current lack of a foundational AI model for specialized process engineering tasks and offers benefits of explainability, knowledge editing, and cost-effectiveness.
arXiv Detail & Related papers (2024-08-28T15:33:47Z)
Using Large Language Models for the Interpretation of Building Regulations [7.013802453969655]
Large language models (LLMs) can generate logically coherent text and source code responding to user prompts. This paper evaluates the performance of LLMs in translating building regulations into LegalRuleML in a few-shot learning setup.
arXiv Detail & Related papers (2024-07-26T08:30:47Z)
CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing [51.00909683314142]
Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. CoCoST framework enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement. CoCoST is validated through rigorous experiments on the DS-1000 and ClassEval datasets.
arXiv Detail & Related papers (2024-03-20T13:33:55Z)
Enhancing Court View Generation with Knowledge Injection and Guidance [43.32071790286732]
Court View Generation (CVG) aims to generate court views based on the plaintiff claims and the fact descriptions. PLMs have showcased their prowess in natural language generation, but their application to the complex, knowledge-intensive domain of CVG often reveals inherent limitations. We present a novel approach, named Knowledge Injection and Guidance (KIG), designed to bolster CVG using PLMs. To efficiently incorporate domain knowledge during the training stage, we introduce a knowledge-injected prompt encoder for prompt tuning, thereby reducing computational overhead.
arXiv Detail & Related papers (2024-03-07T09:51:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.