AraReasoner: Evaluating Reasoning-Based LLMs for Arabic NLP

Large language models (LLMs) have shown remarkable progress in reasoning abilities and general natural language processing (NLP) tasks, yet their performance on Arabic data, characterized by rich morphology, diverse dialects, and complex script, remains underexplored. This paper presents a comprehensive benchmarking study of multiple reasoning-focused LLMs, with a special emphasis on the newly introduced DeepSeek models, across a suite of fifteen Arabic NLP tasks. We experiment with various strategies, including zero-shot, few-shot, and fine-tuning. This allows us to systematically evaluate performance on datasets covering a range of applications to examine their capacity for linguistic reasoning under different levels of complexity. Our experiments reveal several key findings. First, carefully selecting just three in-context examples delivers an average uplift of over 13 F1 points on classification tasks-boosting sentiment analysis from 35.3% to 87.5% and paraphrase detection from 56.1% to 87.0%. Second, reasoning-focused DeepSeek architectures outperform a strong GPT o4-mini baseline by an average of 12 F1 points on complex inference tasks in the zero-shot setting. Third, LoRA-based fine-tuning yields up to an additional 8 points in F1 and BLEU compared to equivalent increases in model scale. The code is available at https://anonymous.4open.science/r/AraReasoner41299

Quantum Graph Transformer for NLP Sentiment Classification

Quantum machine learning is a promising direction for building more efficient and expressive models, particularly in domains where understanding complex, structured data is critical. We present the Quantum Graph Transformer (QGT), a hybrid graph-based architecture that integrates a quantum self-attention mechanism into the message-passing framework for structured language modeling. The attention mechanism is implemented using parameterized quantum circuits (PQCs), which enable the model to capture rich contextual relationships while significantly reducing the number of trainable parameters compared to classical attention mechanisms. We evaluate QGT on five sentiment classification benchmarks. Experimental results show that QGT consistently achieves higher or comparable accuracy than existing quantum natural language processing (QNLP) models, including both attention-based and non-attention-based approaches. When compared with an equivalent classical graph transformer, QGT yields an average accuracy improvement of 5.42% on real-world datasets and 4.76% on synthetic datasets. Additionally, QGT demonstrates improved sample efficiency, requiring nearly 50% fewer labeled samples to reach comparable performance on the Yelp dataset. These results highlight the potential of graph-based QNLP techniques for advancing efficient and scalable language understanding.

Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing

Multi-modal affective computing aims to automatically recognize and interpret human attitudes from diverse data sources such as images and text, thereby enhancing human-computer interaction and emotion understanding. Existing approaches typically rely on unimodal analysis or straightforward fusion of cross-modal information that fail to capture complex and conflicting evidence presented across different modalities. In this paper, we propose a novel LLM-based approach for affective computing that explicitly deconstructs visual and textual representations into shared (modality-invariant) and modality-specific components. Specifically, our approach firstly encodes and aligns input modalities using pre-trained multi-modal encoders, then employs a representation decomposition framework to separate common emotional content from unique cues, and finally integrates these decomposed signals via an attention mechanism to form a dynamic soft prompt for a multi-modal LLM. Extensive experiments on three representative tasks for affective computing, namely, multi-modal aspect-based sentiment analysis, multi-modal emotion analysis, and hateful meme detection, demonstrate the effectiveness of our approach, which consistently outperforms strong baselines and state-of-the-art models.

Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors

Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect Western European or North American biases. This cultural skew can lead to an overestimation of model performance and contributions to NLP progress. However, the impact of cultural bias on metaphor processing, particularly in multimodal contexts, remains largely unexplored. To address this gap, we introduce MultiMM, a Multicultural Multimodal Metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English. MultiMM consists of 8,461 text-image advertisement pairs, each accompanied by fine-grained annotations, providing a deeper understanding of multimodal metaphors beyond a single cultural domain. Additionally, we propose Sentiment-Enriched Metaphor Detection (SEMD), a baseline model that integrates sentiment embeddings to enhance metaphor comprehension across cultural backgrounds. Experimental results validate the effectiveness of SEMD on metaphor detection and sentiment analysis tasks. We hope this work increases awareness of cultural bias in NLP research and contributes to the development of fairer and more inclusive language models. Our dataset and code are available at https://github.com/DUTIR-YSQ/MultiMM.

Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysis

Large language model (LLM) is an effective approach to addressing data scarcity in low-resource scenarios. Recent existing research designs hand-crafted prompts to guide LLM for data augmentation. We introduce a data augmentation strategy for the aspect category sentiment analysis (ACSA) task that preserves the original sentence semantics and has linguistic diversity, specifically by providing a structured prompt template for an LLM to generate predefined content. In addition, we employ a post-processing technique to further ensure semantic consistency between the generated sentence and the original sentence. The augmented data increases the semantic coverage of the training distribution, enabling the model better to understand the relationship between aspect categories and sentiment polarities, enhancing its inference capabilities. Furthermore, we propose a confidence-weighted fine-tuning strategy to encourage the model to generate more confident and accurate sentiment polarity predictions. Compared with powerful and recent works, our method consistently achieves the best performance on four benchmark datasets over all baselines.

Hybrid Extractive Abstractive Summarization for Multilingual Sentiment Analysis

We propose a hybrid approach for multilingual sentiment analysis that combines extractive and abstractive summarization to address the limitations of standalone methods. The model integrates TF-IDF-based extraction with a fine-tuned XLM-R abstractive module, enhanced by dynamic thresholding and cultural adaptation. Experiments across 10 languages show significant improvements over baselines, achieving 0.90 accuracy for English and 0.84 for low-resource languages. The approach also demonstrates 22% greater computational efficiency than traditional methods. Practical applications include real-time brand monitoring and cross-cultural discourse analysis. Future work will focus on optimization for low-resource languages via 8-bit quantization.

How do datasets, developers, and models affect biases in a low-resourced language?

Sociotechnical systems, such as language technologies, frequently exhibit identity-based biases. These biases exacerbate the experiences of historically marginalized communities and remain understudied in low-resource contexts. While models and datasets specific to a language or with multilingual support are commonly recommended to address these biases, this paper empirically tests the effectiveness of such approaches in the context of gender, religion, and nationality-based identities in Bengali, a widely spoken but low-resourced language. We conducted an algorithmic audit of sentiment analysis models built on mBERT and BanglaBERT, which were fine-tuned using all Bengali sentiment analysis (BSA) datasets from Google Dataset Search. Our analyses showed that BSA models exhibit biases across different identity categories despite having similar semantic content and structure. We also examined the inconsistencies and uncertainties arising from combining pre-trained models and datasets created by individuals from diverse demographic backgrounds. We connected these findings to the broader discussions on epistemic injustice, AI alignment, and methodological decisions in algorithmic audits.

CAtCh: Cognitive Assessment through Cookie Thief

Several machine learning algorithms have been developed for the prediction of Alzheimer's disease and related dementia (ADRD) from spontaneous speech. However, none of these algorithms have been translated for the prediction of broader cognitive impairment (CI), which in some cases is a precursor and risk factor of ADRD. In this paper, we evaluated several speech-based open-source methods originally proposed for the prediction of ADRD, as well as methods from multimodal sentiment analysis for the task of predicting CI from patient audio recordings. Results demonstrated that multimodal methods outperformed unimodal ones for CI prediction, and that acoustics-based approaches performed better than linguistics-based ones. Specifically, interpretable acoustic features relating to affect and prosody were found to significantly outperform BERT-based linguistic features and interpretable linguistic features, respectively. All the code developed for this study is available at https://github.com/JTColonel/catch.

Sentiment Analysis in Learning Management Systems Understanding Student Feedback at Scale

During the wake of the Covid-19 pandemic, the educational paradigm has experienced a major change from in person learning traditional to online platforms. The change of learning convention has impacted the teacher-student especially in non-verbal communication. The absent of non-verbal communication has led to a reliance on verbal feedback which diminished the efficacy of the educational experience. This paper explores the integration of sentiment analysis into learning management systems (LMS) to bridge the student-teacher's gap by offering an alternative approach to interpreting student feedback beyond its verbal context. The research involves data preparation, feature selection, and the development of a deep neural network model encompassing word embedding, LSTM, and attention mechanisms. This model is compared against a logistic regression baseline to evaluate its efficacy in understanding student feedback. The study aims to bridge the communication gap between instructors and students in online learning environments, offering insights into the emotional context of student feedback and ultimately improving the quality of online education.

Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis

We investigate the effectiveness of large language models (LLMs), including reasoning-based and non-reasoning models, in performing zero-shot financial sentiment analysis. Using the Financial PhraseBank dataset annotated by domain experts, we evaluate how various LLMs and prompting strategies align with human-labeled sentiment in a financial context. We compare three proprietary LLMs (GPT-4o, GPT-4.1, o3-mini) under different prompting paradigms that simulate System 1 (fast and intuitive) or System 2 (slow and deliberate) thinking and benchmark them against two smaller models (FinBERT-Prosus, FinBERT-Tone) fine-tuned on financial sentiment analysis. Our findings suggest that reasoning, either through prompting or inherent model design, does not improve performance on this task. Surprisingly, the most accurate and human-aligned combination of model and method was GPT-4o without any Chain-of-Thought (CoT) prompting. We further explore how performance is impacted by linguistic complexity and annotation agreement levels, uncovering that reasoning may introduce overthinking, leading to suboptimal predictions. This suggests that for financial sentiment classification, fast, intuitive "System 1"-like thinking aligns more closely with human judgment compared to "System 2"-style slower, deliberative reasoning simulated by reasoning models or CoT prompting. Our results challenge the default assumption that more reasoning always leads to better LLM decisions, particularly in high-stakes financial applications.