paper-with-me

홈 › Papers

Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation

2024-02-19 · Joseph Marvin Imperial, Gail Forey, Harish Tayyar Madabushi

Domain experts across engineering, healthcare, and education follow strict standards for producing quality content such as technical manuals, medication instructions, and children's reading materials. However, current works in controllable text generation have yet to explore using these standards as references for control. Towards this end, we introduce Standardize, a retrieval-style in-context learning-based framework to guide large language models to align with expert-defined standards. Focusing on English language standards in the education domain as a use case, we consider the Common European Framework of Reference for Languages (CEFR) and Common Core Standards (CCS) for the task of open-ended content generation. Our findings show that models can gain a 45% to 100% increase in precise accuracy across open and commercial LLMs evaluated, demonstrating that the use of knowledge artifacts extracted from standards and integrating them in the generation process can effectively guide models to produce better standard-aligned content.

📄 PDF Abstract BibTeX arXiv:2402.12593

Code (1)

imperialite/standardize-ctg 공식 구현 pytorch

Tasks

In-Context LearningRetrievalText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Text-Based Approaches to Item Alignment to Content Standards in Large-Scale Reading & Writing Tests

2025-09-30 · Yanbin Fu, Hong Jiao, Tianyi Zhou, Nan Zhang 외 arxiv

Aligning test items to content standards is a critical step in test development to collect validity evidence based on content. Item alignment has typically been conducted by human experts. This judgmental process can be …

Semantic Similarity

A Standardized Framework for Sensor Placement in Human Motion Capture and Wearable Applications

2024-12-30 · Seyed Yahya Shirazi, Julius Welzel, Sein Jeung, Lara Godbersen

The proliferation of wearable sensors and monitoring technologies has created an urgent need for standardized sensor placement protocols. While existing standards like SENIAM address specific applications, no comprehensi…

Aligning Language Models with Clinical Expertise: DPO for Heart Failure Nursing Documentation in Critical Care

2025-10-06 · Junyi Fan, Li Sun, Negin Ashrafi, Kamiar Alaei 외 arxiv

Nursing documentation in intensive care units (ICUs) provides essential clinical intelligence but often suffers from inconsistent terminology, informal styles, and lack of standardization, challenges that are particularl…

Position: Restructuring of Categories and Implementation of Guidelines Essential for VLM Adoption in Healthcare

2025-05-12 · Amara Tariq, Rimita Lahiri, Charles Kahn, Imon Banerjee

The intricate and multifaceted nature of vision language model (VLM) development, adaptation, and application necessitates the establishment of clear and standardized reporting protocols, particularly within the high-sta…

Position

Human or LLM as Standardized Patients? A Comparative Study for Medical Education

2025-11-12 · Bingquan Zhang, Xiaoxiao Liu, Yuchi Wang, Lei Zhou 외 arxiv

Standardized patients (SPs) are indispensable for clinical skills training but remain expensive and difficult to scale. Although large language model (LLM)-based virtual standardized patients (VSPs) have been proposed as…

Response Generation