Between 2018 and 2020, the field witnessed asurgein the development of these models (Devlin etal.,2019;Liu

This paper presents a transformer-based approach for classifying hope expressions in text. We developed and compared three architectures (BERT, GPT-2, and DeBERTa) for both binary classification (Hope vs. Not Hope) and multiclass categorization (five hope-related categories). Our initial BERT implementation achieved 83.65% binary and 74.87% multiclass accuracy. In the extended comparison, BERT demonstrated superior performance (84.49% binary, 72.03% multiclass accuracy) while requiring significantly fewer computational resources (443s vs. 704s training time) than newer architectures. GPT-2 showed lowest overall accuracy (79.34% binary, 71.29% multiclass), while DeBERTa achieved moderate results (80.70% binary, 71.56% multiclass) but at substantially higher computational cost (947s for multiclass training). Error analysis revealed architecture-specific strengths in detecting nuanced hope expressions, with GPT-2 excelling at sarcasm detection (92.46% recall). This study provides a framework for computational analysis of hope, with applications in mental health and social media analysis, while demonstrating that architectural suitability may outweigh model size for specialized emotion detection tasks.

Fine-grained sentiment analysis faces ongoing challenges in Aspect Sentiment Triple Extraction (ASTE), particularly in accurately capturing the relationships between aspects, opinions, and sentiment polarities. While researchers have made progress using BERT and Graph Neural Networks, the full potential of advanced language models in understanding complex language patterns remains unexplored. We introduce DESS, a new approach that builds upon previous work by integrating DeBERTa's enhanced attention mechanism to better understand context and relationships in text. Our framework maintains a dual-channel structure, where DeBERTa works alongside an LSTM channel to process both meaning and grammatical patterns in text. We have carefully refined how these components work together, paying special attention to how different types of language information interact. When we tested DESS on standard datasets, it showed meaningful improvements over current methods, with F1-score increases of 4.85, 8.36, and 2.42 in identifying aspect opinion pairs and determining sentiment accurately. Looking deeper into the results, we found that DeBERTa's sophisticated attention system helps DESS handle complicated sentence structures better, especially when important words are far apart. Our findings suggest that upgrading to more advanced language models when thoughtfully integrated, can lead to real improvements in how well we can analyze sentiments in text.

Phishing emails continue to pose a persistent challenge to online communication, exploiting human trust and evading automated filters through realistic language and adaptive tactics. While large language models (LLMs) such as GPT-4 and LLaMA-3-8B achieve strong accuracy in text classification, their deployment in security systems requires assessing reliability beyond benchmark performance. To address this, this study introduces the Trustworthiness Calibration Framework (TCF), a reproducible methodology for evaluating phishing detectors across three dimensions: calibration, consistency, and robustness. These components are integrated into a bounded index, the Trustworthiness Calibration Index (TCI), and complemented by the Cross-Dataset Stability (CDS) metric that quantifies stability of trustworthiness across datasets. Experiments conducted on five corpora, such as SecureMail 2025, Phishing Validation 2024, CSDMC2010, Enron-Spam, and Nazario, using DeBERTa-v3-base, LLaMA-3-8B, and GPT-4 demonstrate that GPT-4 achieves the strongest overall trust profile, followed by LLaMA-3-8B and DeBERTa-v3-base. Statistical analysis confirms that reliability varies independently of raw accuracy, underscoring the importance of trust-aware evaluation for real-world deployment. The proposed framework establishes a transparent and reproducible foundation for assessing model dependability in LLM-based phishing detection.

In the absence of sizable training data for most world languages and NLP tasks, translation-based strategies such as translate-test -- evaluating on noisy source language data translated from the target language -- and translate-train -- training on noisy target language data translated from the source language -- have been established as competitive approaches for cross-lingual transfer (XLT). For token classification tasks, these strategies require label projection: mapping the labels from each token in the original sentence to its counterpart(s) in the translation. To this end, it is common to leverage multilingual word aligners (WAs) derived from encoder language models such as mBERT or LaBSE. Despite obvious associations between machine translation (MT) and WA, research on extracting alignments with MT models is largely limited to exploiting cross-attention in encoder-decoder architectures, yielding poor WA results. In this work, in contrast, we propose TransAlign, a novel word aligner that utilizes the encoder of a massively multilingual MT model. We show that TransAlign not only achieves strong WA performance but substantially outperforms popular WA and state-of-the-art non-WA-based label projection methods in MT-based XLT for token classification.

Yanbin Fu, Hong Jiao, Tianyi Zhou, Nan Zhang, Ming Li, Qingshu Xu, Sydney Peters, Robert W. Lissitz University of Maryland, College Park Abstract 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 subjective and time - consuming. This study investigated the performance of fine - tuned small language models (SLMs) for automated item alignment using data from a large - scale standardized reading and writing test for college admissions. Different SLMs were trained for alignment at both domain and skill levels respectively with 10 skills mapped to 4 content domains. The model performance was evaluated in multiple criteria on two testing datasets. The impact of types and sizes of the input data for training was investigated. Results showed that including more item text data led to substantially better model performance, surpassing the improvements induced by sample size inc rease alone. For comparison, supervised machine learning models were trained using the embeddings from the multilingual - E5 - lar ge - instruct model. The study results showed that fine - tuned SLMs consistently outperformed the embedding - based supervised machine learning models, particularly for the more fine - grained skill alignment. To better understand model mis classifications, multiple semantic similarity analysis including pairwise cosine similarity, Kullback - Leibler divergence of embedding distributions, and two - dimension projections of item embeddings were conducted.

Pretrained language models (PLM) achieve surprising performance on the Choice of Plausible Alternatives (COPA) task. However, whether PLMs have truly acquired the ability of causal reasoning remains a question. In this paper, we investigate the problem of semantic similarity bias and reveal the vulnerability of current COPA models by certain attacks. Previous solutions that tackle the superficial cues of unbalanced token distribution still encounter the same problem of semantic bias, even more seriously due to the utilization of more training data. We mitigate this problem by simply adding a regularization loss and experimental results show that this solution not only improves the model's generalization ability, but also assists the models to perform more robustly on a challenging dataset, BCOPA-CE, which has unbiased token distribution and is more difficult for models to distinguish cause and effect.

Recognizing spans of biomedical concepts and their types (e.g., drug or gene) in free text, often called biomedical named entity recognition (NER), is a basic component of information extraction (IE) pipelines. Without a strong NER component, other applications, such as knowledge discovery and information retrieval, are not practical. State-of-the-art in NER shifted from traditional ML models to deep neural networks with transformer-based encoder models (e.g., BERT) emerging as the current standard. However, decoder models (also called large language models or LLMs) are gaining traction in IE. But LLM-driven NER often ignores positional information due to the generative nature of decoder models. Furthermore, they are computationally very expensive (both in inference time and hardware needs). Hence, it is worth exploring if they actually excel at biomedical NER and assess any associated trade-offs (performance vs efficiency). This is exactly what we do in this effort employing the same BIO entity tagging scheme (that retains positional information) using five different datasets with varying proportions of longer entities. Our results show that the LLMs chosen (Mistral and Llama: 8B range) often outperform best encoder models (BERT-(un)cased, BiomedBERT, and DeBERTav3: 300M range) by 2-8% in F-scores except for one dataset, where they equal encoder performance. This gain is more prominent among longer entities of length >= 3 tokens. However, LLMs are one to two orders of magnitude more expensive at inference time and may need cost prohibitive hardware. Thus, when performance differences are small or real time user feedback is needed, encoder models might still be more suitable than LLMs.

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences. Methods such as RiC that directly inject raw reward values into prompts face significant numerical sensitivity issues--for instance, LLMs may fail to distinguish between 9.11 and 9.8--while alternatives like MORLHF, Rewarded Soups, and MODPO incur high computational costs by training multiple models. In this work, we introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations. Our approach leverages a diverse set of strictly increasing, non-linear utility functions to transform user-specified preferences into symbolic tokens, which are then used to condition a single LLM. This design not only mitigates numerical reasoning challenges but also substantially reduces training overhead, yielding models that achieve superior Pareto fronts and robust alignment across complex reward dimensions.