ALBERT: Advanced Localization and Bidirectional Encoder Representations from Transformers for Automotive Damage Evaluation

This paper introduces ALBERT, an instance segmentation model specifically designed for comprehensive car damage and part segmentation. Leveraging the power of Bidirectional Encoder Representations, ALBERT incorporates advanced localization mechanisms to accurately identify and differentiate between real and fake damages, as well as segment individual car parts. The model is trained on a large-scale, richly annotated automotive dataset that categorizes damage into 26 types, identifies 7 fake damage variants, and segments 61 distinct car parts. Our approach demonstrates strong performance in both segmentation accuracy and damage classification, paving the way for intelligent automotive inspection and assessment applications.

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification

Purpose: This study proposes a framework for fine-tuning large language models (LLMs) with differential privacy (DP) to perform multi-abnormality classification on radiology report text. By injecting calibrated noise during fine-tuning, the framework seeks to mitigate the privacy risks associated with sensitive patient data and protect against data leakage while maintaining classification performance. Materials and Methods: We used 50,232 radiology reports from the publicly available MIMIC-CXR chest radiography and CT-RATE computed tomography datasets, collected between 2011 and 2019. Fine-tuning of LLMs was conducted to classify 14 labels from MIMIC-CXR dataset, and 18 labels from CT-RATE dataset using Differentially Private Low-Rank Adaptation (DP-LoRA) in high and moderate privacy regimes (across a range of privacy budgets = {0.01, 0.1, 1.0, 10.0}). Model performance was evaluated using weighted F1 score across three model architectures: BERT-medium, BERT-small, and ALBERT-base. Statistical analyses compared model performance across different privacy levels to quantify the privacy-utility trade-off. Results: We observe a clear privacy-utility trade-off through our experiments on 2 different datasets and 3 different models. Under moderate privacy guarantees the DP fine-tuned models achieved comparable weighted F1 scores of 0.88 on MIMIC-CXR and 0.59 on CT-RATE, compared to non-private LoRA baselines of 0.90 and 0.78, respectively. Conclusion: Differentially private fine-tuning using LoRA enables effective and privacy-preserving multi-abnormality classification from radiology reports, addressing a key challenge in fine-tuning LLMs on sensitive medical data.

Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts

Quantifying the realism of images remains a challenging problem in the field of artificial intelligence. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein's death. We introduce a novel method for assessing image realism using Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI). Our approach is based on the premise that LVLMs may generate hallucinations when confronted with images that defy common sense. Using LVLM to extract atomic facts from these images, we obtain a mix of accurate facts and erroneous hallucinations. We proceed by calculating pairwise entailment scores among these facts, subsequently aggregating these values to yield a singular reality score. This process serves to identify contradictions between genuine facts and hallucinatory elements, signaling the presence of images that violate common sense. Our approach has achieved a new state-of-the-art performance in zero-shot mode on the WHOOPS! dataset.

Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility

Despite advances in language modelling, distributional methods that build semantic representations from co-occurrences fail to discriminate between plausible and implausible events. In this work, we investigate how plausibility prediction can be improved by injecting latent knowledge prompted from large language models using parameter-efficient fine-tuning. We train 12 task adapters to learn various physical properties and association measures and perform adapter fusion to compose latent semantic knowledge from each task on top of pre-trained AlBERT embeddings. We automate auxiliary task data generation, which enables us to scale our approach and fine-tune our learned representations across two plausibility datasets. Our code is available at https://github.com/Jacob-Chmura/plausibility-vaccine.

EPEE: Towards Efficient and Effective Foundation Models in Biomedicine

Foundation models, including language models, e.g., GPT, and vision models, e.g., CLIP, have significantly advanced numerous biomedical tasks. Despite these advancements, the high inference latency and the "overthinking" issues in model inference impair the efficiency and effectiveness of foundation models, thus limiting their application in real-time clinical settings. To address these challenges, we proposed EPEE (Entropy- and Patience-based Early Exiting), a novel hybrid strategy designed to improve the inference efficiency of foundation models. The core idea was to leverage the strengths of entropy-based and patience-based early exiting methods to overcome their respective weaknesses. To evaluate EPEE, we conducted experiments on three core biomedical tasks-classification, relation extraction, and event extraction-using four foundation models (BERT, ALBERT, GPT-2, and ViT) across twelve datasets, including clinical notes and medical images. The results showed that EPEE significantly reduced inference time while maintaining or improving accuracy, demonstrating its adaptability to diverse datasets and tasks. EPEE addressed critical barriers to deploying foundation models in healthcare by balancing efficiency and effectiveness. It potentially provided a practical solution for real-time clinical decision-making with foundation models, supporting reliable and efficient workflows.

Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media

Social media platforms provide valuable insights into mental health trends by capturing user-generated discussions on conditions such as depression, anxiety, and suicidal ideation. Machine learning (ML) and deep learning (DL) models have been increasingly applied to classify mental health conditions from textual data, but selecting the most effective model involves trade-offs in accuracy, interpretability, and computational efficiency. This study evaluates multiple ML models, including logistic regression, random forest, and LightGBM, alongside deep learning architectures such as ALBERT and Gated Recurrent Units (GRUs), for both binary and multi-class classification of mental health conditions. Our findings indicate that ML and DL models achieve comparable classification performance on medium-sized datasets, with ML models offering greater interpretability through variable importance scores, while DL models are more robust to complex linguistic patterns. Additionally, ML models require explicit feature engineering, whereas DL models learn hierarchical representations directly from text. Logistic regression provides the advantage of capturing both positive and negative associations between features and mental health conditions, whereas tree-based models prioritize decision-making power through split-based feature selection. This study offers empirical insights into the advantages and limitations of different modeling approaches and provides recommendations for selecting appropriate methods based on dataset size, interpretability needs, and computational constraints.

Robust Bias Detection in MLMs and its Application to Human Trait Ratings

There has been significant prior work using templates to study bias against demographic attributes in MLMs. However, these have limitations: they overlook random variability of templates and target concepts analyzed, assume equality amongst templates, and overlook bias quantification. Addressing these, we propose a systematic statistical approach to assess bias in MLMs, using mixed models to account for random effects, pseudo-perplexity weights for sentences derived from templates and quantify bias using statistical effect sizes. Replicating prior studies, we match on bias scores in magnitude and direction with small to medium effect sizes. Next, we explore the novel problem of gender bias in the context of $\textit{personality}$ and $\textit{character}$ traits, across seven MLMs (base and large). We find that MLMs vary; ALBERT is unbiased for binary gender but the most biased for non-binary $\textit{neo}$, while RoBERTa-large is the most biased for binary gender but shows small to no bias for $\textit{neo}$. There is some alignment of MLM bias and findings in psychology (human perspective) - in $\textit{agreeableness}$ with RoBERTa-large and $\textit{emotional stability}$ with BERT-large. There is general agreement for the remaining 3 personality dimensions: both sides observe at most small differences across gender. For character traits, human studies on gender bias are limited thus comparisons are not feasible.

Meursault as a Data Point

In an era dominated by datafication, the reduction of human experiences to quantifiable metrics raises profound philosophical and ethical questions. This paper explores these issues through the lens of Meursault, the protagonist of Albert Camus' The Stranger, whose emotionally detached existence epitomizes the existential concept of absurdity. Using natural language processing (NLP) techniques including emotion detection (BERT), sentiment analysis (VADER), and named entity recognition (spaCy)-this study quantifies key events and behaviors in Meursault's life. Our analysis reveals the inherent limitations of applying algorithmic models to complex human experiences, particularly those rooted in existential alienation and moral ambiguity. By examining how modern AI tools misinterpret Meursault's actions and emotions, this research underscores the broader ethical dilemmas of reducing nuanced human narratives to data points, challenging the foundational assumptions of our data-driven society. The findings presented in this paper serve as a critique of the increasing reliance on data-driven narratives and advocate for incorporating humanistic values in artificial intelligence.

Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble techniques to improve sentence embeddings. We use external data from SimpleWiki, Wikipedia, and BookCorpus to make sure the training data is consistent. The framework includes a hierarchical model with an encoding layer, refinement layer, and ensemble prediction layer, using ALBERT-xxlarge, RoBERTa-large, and DeBERTa-large models. Cross-attention layers combine external context, and data augmentation techniques like synonym replacement and back-translation increase data variety. Experimental results show large improvements in accuracy and F1-score compared to basic models, and studies confirm that cross-attention and data augmentation make a difference. This work presents an effective way to improve sentence embedding tasks and lays the groundwork for future NLP research.

Evaluation and Efficiency Comparison of Evolutionary Algorithms for Service Placement Optimization in Fog Architectures

This study compares three evolutionary algorithms for the problem of fog service placement: weighted sum genetic algorithm (WSGA), non-dominated sorting genetic algorithm II (NSGA-II), and multiobjective evolutionary algorithm based on decomposition (MOEA/D). A model for the problem domain (fog architecture and fog applications) and for the optimization (objective functions and solutions) is presented. Our main concerns are related to optimize the network latency, the service spread and the use of the resources. The algorithms are evaluated with a random Barabasi-Albert network topology with 100 devices and with two experiment sizes of 100 and 200 application services. The results showed that NSGA-II obtained the highest optimizations of the objectives and the highest diversity of the solution space. On the contrary, MOEA/D was better to reduce the execution times. The WSGA algorithm did not show any benefit with regard to the other two algorithms.