The qualitative identification of weld defects is crucial for the safe use and life assessment of in-service welded components. Although intelligent defect recognition using machine learning has gained significant attention, existing approaches often suffer from limited defect types, small datasets, and reliance on single-feature sources. Consequently, the recognition accuracy remains insufficient for real-world industrial applications, especially when encountering new and complex defect patterns. To address these challenges, this study proposes a signal-image-joint machine learning fusion model (SIJ-MLF) that classifies weld defects using large-scale data collected from austenitic stainless steel weld samples. The method integrates multiple features extracted from both defect pulse signals and images, adaptive sliding window and feature selection techniques are introduced to further enhance recognition performance. Comparative analyses demonstrate that the proposed approach achieves a stable accuracy of up to 96% when tested on completely new practical samples. Moreover, an intelligent recognition software has been developed based on this work, illustrating its potential for reliable and efficient industrial inspection.

Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot or few-shot settings may be affected by task contamination, a potential limitation that has not been thoroughly examined. This paper investigates how zero-shot and few-shot performance of LLMs has changed chronologically over datasets released over time, and over LLMs released over time. Utilizing GPT-3 series models and several other recent open-sourced LLMs, and controlling for dataset difficulty, we find that datasets released prior to the LLM training data creation date perform surprisingly better than datasets released post the LLM training data creation date. This strongly indicates that, for many LLMs, there exists task contamination on zero-shot and few-shot evaluation for datasets prior to the LLMs' training data creation date. Additionally, we utilize training data inspection, training data extraction, and a membership inference attack, which reveal further evidence of task contamination. Importantly, we find that for tasks with no possibility of task contamination, LLMs rarely demonstrate statistically significant improvements over simple majority baselines, in both zero and few-shot settings.

Predicting the future is of great interest across many aspects of human activity. Businesses are interested in future trends, traders are interested in future stock prices, and companies are highly interested in future technological breakthroughs. While there are many automated systems for predicting future numerical data, such as weather, stock prices, and demand for products, there is relatively little work in automatically predicting textual data. Humans are interested in textual data predictions because it is a natural format for our consumption, and experts routinely make predictions in a textual format (Christensen et al., 2004; Tetlock & Gardner, 2015; Frick, 2015). However, there has been relatively little formalization of this general problem in the machine learning or natural language processing communities. To address this gap, we introduce the task of future language modeling: probabilistic modeling of texts in the future based on a temporal history of texts. To our knowledge, our work is the first work to formalize the task of predicting the future in this way. We show that it is indeed possible to build future language models that improve upon strong non-temporal language model baselines, opening the door to working on this important, and widely applicable problem.

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue.First, three language modeling tasks are used to pre-train the transformers, token-and utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts.Then, multitask learning between the utterance prediction and the token span prediction is applied to finetune for span-based question answering (QA).Our approach is evaluated on the FRIENDSQA dataset and shows improvements of 3.8% and 1.4% over the two state-of-the-art transformer models, BERT and RoBERTa, respectively.

This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates.A total of 6,492 resumes are extracted from 24,933 job applications for 252 positions designated into four levels of experience for Clinical Research Coordinators (CRC).Each resume is manually annotated to its most appropriate CRC position by experts through several rounds of triple annotation to establish guidelines.As a result, a high Kappa score of 61% is achieved for interannotator agreement.Given this dataset, novel transformer-based classification models are developed for two tasks: the first task takes a resume and classifies it to a CRC level (T1), and the second task takes both a resume and a job description to apply and predicts if the application is suited to the job (T2).Our best models using section encoding and multi-head attention decoding give results of 73.3% to T1 and 79.2% to T2.Our analysis shows that the prediction errors are mostly made among adjacent CRC levels, which are hard for even experts to distinguish, implying the practical value of our models in real HR platforms.