BengaliSent140: A Large-Scale Bengali Binary Sentiment Dataset for Hate and Non-Hate Speech Classification

Sentiment analysis for the Bengali language has attracted increasing research interest in recent years. However, progress remains constrained by the scarcity of large-scale and diverse annotated datasets. Although several Bengali sentiment and hate speech datasets are publicly available, most are limited in size or confined to a single domain, such as social media comments. Consequently, these resources are often insufficient for training modern deep learning based models, which require large volumes of heterogeneous data to learn robust and generalizable representations. In this work, we introduce BengaliSent140, a large-scale Bengali binary sentiment dataset constructed by consolidating seven existing Bengali text datasets into a unified corpus. To ensure consistency across sources, heterogeneous annotation schemes are systematically harmonized into a binary sentiment formulation with two classes: Not Hate (0) and Hate (1). The resulting dataset comprises 139,792 unique text samples, including 68,548 hate and 71,244 not-hate instances, yielding a relatively balanced class distribution. By integrating data from multiple sources and domains, BengaliSent140 offers broader linguistic and contextual coverage than existing Bengali sentiment datasets and provides a strong foundation for training and benchmarking deep learning models. Baseline experimental results are also reported to demonstrate the practical usability of the dataset. The dataset is publicly available at https://www.kaggle.com/datasets/akifislam/bengalisent140/

Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning

Copy trading has become the dominant entry strategy in meme coin markets. However, due to the market's extreme illiquid and volatile nature, the strategy exposes an exploitable attack surface: adversaries deploy manipulative bots to front-run trades, conceal positions, and fabricate sentiment, systematically extracting value from naïve copiers at scale. Despite its prevalence, bot-driven manipulation remains largely unexplored, and no robust defensive framework exists. We propose a manipulation-resistant copy-trading system based on a multi-agent architecture powered by a multi-modal, explainable large language model (LLM). Our system decomposes copy trading into three specialized agents for coin evaluation, wallet selection, and timing assessment. Evaluated on historical data from over 6,000 meme coins, our approach outperforms zero-shot and most statistic-driven baselines in prediction accuracy as well as all baselines in economic performance, achieving an average return of 14% for identified smart-money trades and an estimated copier return of 3% per trade under realistic market frictions. Overall, our results demonstrate the effectiveness of agent-based defenses and predictability of trader profitability in adversarial meme coin markets, providing a practical foundation for robust copy trading.

MEGnifying Emotion: Sentiment Analysis from Annotated Brain Data

Decoding emotion from brain activity could unlock a deeper understanding of the human experience. While a number of existing datasets align brain data with speech and with speech transcripts, no datasets have annotated brain data with sentiment. To bridge this gap, we explore the use of pre-trained Text-to-Sentiment models to annotate non invasive brain recordings, acquired using magnetoencephalography (MEG), while participants listened to audiobooks. Having annotated the text, we employ force-alignment of the text and audio to align our sentiment labels with the brain recordings. It is straightforward then to train Brainto-Sentiment models on these data. Experimental results show an improvement in balanced accuracy for Brain-to-Sentiment compared to baseline, supporting the proposed approach as a proof-of-concept for leveraging existing MEG datasets and learning to decode sentiment directly from the brain.

AGSP-DSA: An Adaptive Graph Signal Processing Framework for Robust Multimodal Fusion with Dynamic Semantic Alignment

In this paper, we introduce an Adaptive Graph Signal Processing with Dynamic Semantic Alignment (AGSP DSA) framework to perform robust multimodal data fusion over heterogeneous sources, including text, audio, and images. The requested approach uses a dual-graph construction to learn both intra-modal and inter-modal relations, spectral graph filtering to boost the informative signals, and effective node embedding with Multi-scale Graph Convolutional Networks (GCNs). Semantic aware attention mechanism: each modality may dynamically contribute to the context with respect to contextual relevance. The experimental outcomes on three benchmark datasets, including CMU-MOSEI, AVE, and MM-IMDB, show that AGSP-DSA performs as the state of the art. More precisely, it achieves 95.3% accuracy, 0.936 F1-score, and 0.924 mAP on CMU-MOSEI, improving MM-GNN by 2.6 percent in accuracy. It gets 93.4% accuracy and 0.911 F1-score on AVE and 91.8% accuracy and 0.886 F1-score on MM-IMDB, which demonstrate good generalization and robustness in the missing modality setting. These findings verify the efficiency of AGSP-DSA in promoting multimodal learning in sentiment analysis, event recognition and multimedia classification.

UrduLM: A Resource-Efficient Monolingual Urdu Language Model

Urdu, spoken by 230 million people worldwide, lacks dedicated transformer-based language models and curated corpora. While multilingual models provide limited Urdu support, they suffer from poor performance, high computational costs, and cultural inaccuracies due to insufficient training data. To address these challenges, we present UrduLM, a pretrained Urdu monolingual language model trained in low-resource settings. We curate a 33GB Urdu corpus from diverse sources, develop a custom BPE tokenizer that reduces tokenization overhead by atleast 20-30% compared to multilingual alternatives, and pretrain a 100M-parameter decoder-only model. In few-shot evaluations, UrduLM achieves competitive performance with multilingual models up to 30x its size, reaching 66.6% accuracy on sentiment classification and BLEU scores exceeding 30 on grammar correction tasks. The complete methodology -- including corpus, tokenizer, model weights, and evaluation benchmarks -- is released openly to establish a baseline for Urdu NLP research and provide a scalable framework for other underrepresented languages.

AI-based approach to burnout identification from textual data

This study introduces an AI-based methodology that utilizes natural language processing (NLP) to detect burnout from textual data. The approach relies on a RuBERT model originally trained for sentiment analysis and subsequently fine-tuned for burnout detection using two data sources: synthetic sentences generated with ChatGPT and user comments collected from Russian YouTube videos about burnout. The resulting model assigns a burnout probability to input texts and can be applied to process large volumes of written communication for monitoring burnout-related language signals in high-stress work environments.

Auditing Disability Representation in Vision-Language Models

Vision-language models (VLMs) are increasingly deployed in socially sensitive applications, yet their behavior with respect to disability remains underexplored. We study disability aware descriptions for person centric images, where models often transition from evidence grounded factual description to interpretation shift including introduction of unsupported inferences beyond observable visual evidence. To systematically analyze this phenomenon, we introduce a benchmark based on paired Neutral Prompts (NP) and Disability-Contextualised Prompts (DP) and evaluate 15 state-of-the-art open- and closed-source VLMs under a zero-shot setting across 9 disability categories. Our evaluation framework treats interpretive fidelity as core objective and combines standard text-based metrics capturing affective degradation through shifts in sentiment, social regard and response length with an LLM-as-judge protocol, validated by annotators with lived experience of disability. We find that introducing disability context consistently degrades interpretive fidelity, inducing interpretation shifts characterised by speculative inference, narrative elaboration, affective degradation and deficit oriented framing. These effects are further amplified along race and gender dimension. Finally, we demonstrate targeted prompting and preference fine-tuning effectively improves interpretive fidelity and reduces substantially interpretation shifts.

Status Hierarchies in Language Models

From school playgrounds to corporate boardrooms, status hierarchies -- rank orderings based on respect and perceived competence -- are universal features of human social organization. Language models trained on human-generated text inevitably encounter these hierarchical patterns embedded in language, raising the question of whether they might reproduce such dynamics in multi-agent settings. This thesis investigates when and how language models form status hierarchies by adapting Berger et al.'s (1972) expectation states framework. I create multi-agent scenarios where separate language model instances complete sentiment classification tasks, are introduced with varying status characteristics (e.g., credentials, expertise), then have opportunities to revise their initial judgments after observing their partner's responses. The dependent variable is deference, the rate at which models shift their ratings toward their partner's position based on status cues rather than task information. Results show that language models form significant status hierarchies when capability is equal (35 percentage point asymmetry, p < .001), but capability differences dominate status cues, with the most striking effect being that high-status assignments reduce higher-capability models' deference rather than increasing lower-capability models' deference. The implications for AI safety are significant: status-seeking behavior could introduce deceptive strategies, amplify discriminatory biases, and scale across distributed deployments far faster than human hierarchies form organically. This work identifies emergent social behaviors in AI systems and highlights a previously underexplored dimension of the alignment challenge.

Boltzmann-GPT: Bridging Energy-Based World Models and Language Generation

Large Language Models (LLMs) generate fluent text, yet whether they truly understand the world or merely produce plausible language about it remains contested. We propose an architectural principle, the mouth is not the brain, that explicitly separates world models from language models. Our architecture comprises three components: a Deep Boltzmann Machine (DBM) that captures domain structure as an energy-based world model, an adapter that projects latent belief states into embedding space, and a frozen GPT-2 that provides linguistic competence without domain knowledge. We instantiate this framework in the consumer review domain using Amazon smartphone reviews. Experiments demonstrate that (1) conditioning through the world model yields significantly higher sentiment correlation, lower perplexity, and greater semantic similarity compared to prompt-based generation alone; (2) the DBM's energy function distinguishes coherent from incoherent market configurations, assigning higher energy to implausible brand-price combinations; and (3) interventions on specific attributes propagate causally to generated text with intervened outputs exhibiting distributions statistically consistent with naturally occurring samples sharing the target configuration. These findings suggest that even small-scale language models can achieve consistent, controllable generation when connected to an appropriate world model, providing empirical support for separating linguistic competence from world understanding.

Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis

Fine-grained opinion analysis of text provides a detailed understanding of expressed sentiments, including the addressed entity. Although this level of detail is sound, it requires considerable human effort and substantial cost to annotate opinions in datasets for training models, especially across diverse domains and real-world applications. We explore the feasibility of LLMs as automatic annotators for fine-grained opinion analysis, addressing the shortage of domain-specific labelled datasets. In this work, we use a declarative annotation pipeline. This approach reduces the variability of manual prompt engineering when using LLMs to identify fine-grained opinion spans in text. We also present a novel methodology for an LLM to adjudicate multiple labels and produce final annotations. After trialling the pipeline with models of different sizes for the Aspect Sentiment Triplet Extraction (ASTE) and Aspect-Category-Opinion-Sentiment (ACOS) analysis tasks, we show that LLMs can serve as automatic annotators and adjudicators, achieving high Inter-Annotator Agreement across individual LLM-based annotators. This reduces the cost and human effort needed to create these fine-grained opinion-annotated datasets.