Extracting fine-grained OCR text from aged documents in diacritic languages remains challenging due to unexpected artifacts, time-induced degradation, and lack of datasets. While standalone spell correction approaches have been proposed, they show limited performance for historical documents due to numerous possible OCR error combinations and differences between modern and classical corpus distributions. We propose a method utilizing available content-focused ebooks as a reference base to correct imperfect OCR-generated text, supported by large language models. This technique generates high-precision pseudo-page-to-page labels for diacritic languages, where small strokes pose significant challenges in historical conditions. The pipeline eliminates various types of noise from aged documents and addresses issues such as missing characters, words, and disordered sequences. Our post-processing method, which generated a large OCR dataset of classical Vietnamese books, achieved a mean grading score of 8.72 on a 10-point scale. This outperformed the state-of-the-art transformer-based Vietnamese spell correction model, which scored 7.03, when evaluated on a sampled subset of the dataset. We also trained a baseline OCR model to assess and compare it with well-known engines. Experimental results demonstrate the strength of our baseline model compared to widely used open-source solutions. The resulting dataset will be released publicly to support future studies.

Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers when allowed to observe their prior answers to the same question in a multi-turn conversation. To understand which types of questions invite more biased answers, we test LLMs on our proposed set of questions that span 9 topics and belong to three types: (1) Subjective; (2) Random; and (3) Objective. Interestingly, LLMs are able to "de-bias" themselves in a multi-turn conversation in response to questions that seek a Random, unbiased answer. Furthermore, we propose B-score, a novel metric that is effective in detecting biases in Subjective, Random, Easy, and Hard questions. On MMLU, HLE, and CSQA, leveraging B-score substantially improves the verification accuracy of LLM answers (i.e, accepting LLM correct answers and rejecting incorrect ones) compared to using verbalized confidence scores or the frequency of single-turn answers alone. Code and data are available at: b-score.github.io.

Neural Architecture Search (NAS) aims to automate the process of architecture design to alleviate the burden of manual trial-and-error when seeking top-performing neural networks for certain tasks. Traditional NAS methods perform network evaluations with full network training, typically incurring hundreds of training epochs for each candidate architecture. Such expensive search costs are infeasible in real-world applications. Several zero-cost metrics, which are computed based on randomly initialized network weights, have been proposed for efficiently estimating architecture quality as a proxy for network accuracy performance. These metrics require much less computation time but may not exhibit sufficient correlation with the actual accuracy. Using a single proxy metric might mislead the search, especially in the region of good-performing architectures in the search space. In this paper, we propose a two-phase Evolutionary Neural Architecture Search with Zero-Cost Proxy-Based Hierarchical Initialization (eNAS-HI) framework. A tree search algorithm, guided by three training-free performance proxy metrics, is used to prune the search space and efficiently identify a diverse set of promising architectures in the initialization phase. These architectures then serve as the initial population for a genetic algorithm in the subsequent evolution phase. The diversity and quality of the initial population help eNAS-HI in finding top-performing architectures with reduced search costs.

Neural Architecture Search (NAS) aims to automate the discovery of high-performing deep neural network architectures. Traditional objective-based NAS approaches typically optimize a certain performance metric (e.g., prediction accuracy), overlooking large parts of the architecture search space that potentially contain interesting network configurations. Furthermore, objective-driven population-based metaheuristics in complex search spaces often quickly exhaust population diversity and succumb to premature convergence to local optima. This issue becomes more complicated in NAS when performance objectives do not fully align with the actual performance of the candidate architectures, as is often the case with training-free metrics. While training-free metrics have gained popularity for their rapid performance estimation of candidate architectures without incurring computation-heavy network training, their effective incorporation into NAS remains a challenge. This paper presents the Pareto Dominance-based Novelty Search for multi-objective NAS with Multiple Training-Free metrics (MTF-PDNS). Unlike conventional NAS methods that optimize explicit objectives, MTF-PDNS promotes population diversity by utilizing a novelty score calculated based on multiple training-free performance and complexity metrics, thereby yielding a broader exploration of the search space. Experimental results on standard NAS benchmark suites demonstrate that MTF-PDNS outperforms conventional methods driven by explicit objectives in terms of convergence speed, diversity maintenance, architecture transferability, and computational costs.

Multi-Objective Evolutionary Neural Architecture Search (MOENAS) methods employ evolutionary algorithms to approximate a set of architectures representing optimal trade-offs between network performance and complexity. Directly estimating network performance via error rates or losses incurs long runtimes due to the computationally expensive network training procedure. Instead, low-cost metrics that require no network training have been proposed as a proxy for network performance. However, these metrics might exhibit inconsistent correlations with network performance across different search spaces . The influences of training-based and training-free metrics on the effectiveness and efficiency of MOENAS are still under-explored. We introduce the Enhanced Training-Free MOENAS (E-TF-MOENAS) that employs the widely-used NSGA-II as the search algorithm and optimizes multiple training-free performance metrics as separate objectives. Experiments on NAS-Bench-101 and NAS-Bench-201 show that E-TF-MOENAS outperforms training-free methods that use a single training-free performance metric and could obtain comparable results to training-based methods but with approximately 30 times less computation cost. E-TF-MOENAS obtains architectures in NAS-Bench-201 with state-of-the-art mean accuracies of 94.37%, 73.50%, and 46.62% for CIFAR-10, CIFAR-100, and ImageNet16-120, respectively, within less than 3 GPU hours. It is beneficial to utilize multiple training-free proxy metrics simultaneously and E-TF-MOENAS provides a convenient framework for building such an efficient NAS approach. The source code can be found at https://github.com/ELO-Lab/E-TF-MOENAS .