← Back to all news
arXiv Machine Learning By Kristoffer Hjelmen Nesland (University of Stavanger, Stavanger, Norway, Solution Seeker AS, Oslo, Norway), Bjarne Grimstad (Solution Seeker AS, Oslo, Norway), Antorweep Chakravorty (University of Stavanger, Stavanger, Norway), Dan Sui (University of Stavanger, Stavanger, Norway)

Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance

Read the original on arXiv Machine Learning →

The paper introduces a text-informed training data filtering approach that uses large language models to combine unstructured operational text with tabular sensor data for anomaly detection and dataset masking. Applied to a virtual flow meter for oil and gas, the multimodal method reduces mean absolute percentage error from 7.1% to 5.4% compared to sensor-only filtering. Ablation studies confirm that operator comments provide additional filtering signals beyond sensor data alone.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 10

Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets

The paper introduces XTF, an explainable token‑level noise filtering framework for fine‑tuning large language models. XTF breaks down token contributions into reasoning importance, knowledge novelty, and task relevance, scores them, and masks gradients of noisy tokens to improve fine‑tuning. Experiments on math, code, and medicine tasks across seven LLMs show up to a 13.7% performance boost over standard fine‑tuning.

By Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren
llmsfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Oct 7

A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company

The paper presents a two‑stage multivariate monitoring framework for high‑dimensional, temporally dependent data from end‑of‑line testing in automotive manufacturing. Stage one cleans and aligns the data, while stage two applies nonlinear dimensionality reduction and a control‑chart‑based anomaly detection procedure that can operate in unsupervised or supervised modes. Applied to Ford Motor Company production data, the framework outperforms the existing model, raising accuracy from 0.50 to 0.625, recall from 0.30 to 1.00, and F1 score from 0.429 to 0.769.

By Mohammad N. Bisheh, Mehrdad Moradi, Parinaz Farajiparvar, Colin Brady, Rajesh Gupta, Xueling Li, Javad Navaei, Milad Parvaneh, Kamran Paynabar
More like this →