Mehwish Nasim

Mehwish Nasim, Sanjeevan Selvaganapathy, Neel Ganapathi Sabhahit et al.

Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they speak when culture is only implied by the situation? We evaluate 60 culturally grounded conversational scenarios across five languages in three conditions: a neutral baseline (Prompt A), an explicit cultural instruction (Prompt B), and implicit situational cueing (Prompt C). We score responses on 12 pragmatic features covering deference to authority, individual-versus-group framing, and uncertainty management. We define Pragmatic Context Sensitivity (PCS) as the fraction of the Prompt A->B shift that reappears under Prompt A->C. Across four deployed LLMs and five languages (English, German, Hindi, Nepali, Urdu), the primary stable-only PCS mean is 0.196 (SD = 0.113), indicating that the models recover only about one-fifth of the pragmatic shift they can produce when instructed explicitly. Transfer is strongest for authority-related cues (0.299) and weakest for individual-versus-group framing (0.120). Uncertainty-related behaviour is mixed: hedging density exhibits negative explicit gaps in all five languages, suggesting that alignment training actively suppresses the target behaviour. Because Hindi and Urdu share core grammar yet index distinct cultural communities, we use them as a natural control; a paired analysis finds no reliable baseline difference (t = 0.96, p = 0.339, dz = 0.06), suggesting that models respond primarily to linguistic structure rather than to the cultural associations a language carries. We argue that multilingual cultural pragmatics is an explicit-versus-implicit deployment problem, not only a factual knowledge problem.

Sahil Tripathi, Gautam Siddharth Kashyap, Mehwish Nasim et al.

Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusion-based methods to in-context learning with Large Vision-Language Models (LVLMs), have made progress but remain limited by three factors: i) cultural blindness (missing symbolic context), ii) boundary ambiguity (satire vs. abuse confusion), and iii) lack of interpretability (opaque model reasoning). We introduce CROSS-ALIGN+, a three-stage framework that systematically addresses these limitations: (1) Stage I mitigates cultural blindness by enriching multimodal representations with structured knowledge from ConceptNet, Wikidata, and Hatebase; (2) Stage II reduces boundary ambiguity through parameter-efficient LoRA adapters that sharpen decision boundaries; and (3) Stage III enhances interpretability by generating cascaded explanations. Extensive experiments on five benchmarks and eight LVLMs demonstrate that CROSS-ALIGN+ consistently outperforms state-of-the-art methods, achieving up to 17% relative F1 improvement while providing interpretable justifications for each decision.

Pranav Bhandari, Usman Naseem, Mehwish Nasim

Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whether this assumption holds by analysing the geometric relationships between Big Five personality steering directions. We study steering vectors extracted from two model families (LLaMA-3-8B and Mistral-8B) and apply a range of geometric conditioning schemes, from unconstrained directions to soft and hard orthonormalisation. Our results show that personality steering directions exhibit substantial geometric dependence: steering one trait consistently induces changes in others, even when linear overlap is explicitly removed. While hard orthonormalisation enforces geometric independence, it does not eliminate cross-trait behavioural effects and can reduce steering strength. These findings suggest that personality traits in LLMs occupy a slightly coupled subspace, limiting fully independent trait control.

Afrozah Nadeem, Agrima Seth, Mehwish Nasim et al.

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to political bias in LLMs, prior work largely focuses on high-resource, Western languages or narrow multilingual settings, leaving cross-lingual consistency and safe post-hoc mitigation underexplored. To address this gap, we present a large-scale multilingual evaluation of political bias spanning 50 countries and 33 languages. We introduce a complementary post-hoc mitigation framework, Cross-Lingual Alignment Steering (CLAS), designed to augment existing steering methods by aligning ideological representations across languages and dynamically regulating intervention strength. This method aligns latent ideological representations induced by political prompts into a shared ideological subspace, ensuring cross lingual consistency, with the adaptive mechanism prevents over correction and preserves coherence. Experiments demonstrate substantial bias reduction along both economic and social axes with minimal degradation in response quality. The proposed framework establishes a scalable and interpretable paradigm for fairness-aware multilingual LLM governance, balancing ideological neutrality with linguistic and cultural diversity.

Pranav Bhandari, Usman Naseem, Amitava Datta et al.

Psychological assessment tools have long helped humans understand behavioural patterns. While Large Language Models (LLMs) can generate content comparable to that of humans, we explore whether they exhibit personality traits. To this end, this work applies psychological tools to LLMs in diverse scenarios to generate personality profiles. Using established trait-based questionnaires such as the Big Five Inventory and by addressing the possibility of training data contamination, we examine the dimensional variability and dominance of LLMs across five core personality dimensions: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. Our findings reveal that LLMs exhibit unique dominant traits, varying characteristics, and distinct personality profiles even within the same family of models.

Weijia Liu, Bo Miao, Jiuxin Cao et al.

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These semantics are integrated with visual features for producing discriminative video representations. Finally, a language-conditioned transformer is designed to decode free-form language queries, on the fly, using aligned video representations for moment retrieval. Extensive experiments demonstrate that LMR achieves state-of-the-art results, outperforming the nearest competitor by up to 3.28\% and 4.06\% on the challenging QVHighlights and Charades-STA benchmarks, respectively. More importantly, the performance gains are significantly higher for localization of complex queries.

Pranav Bhandari, Nicolas Fay, Michael Wise et al.

Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions. Adherence to psychological traits lacks comprehensive analysis, especially in the case of dyadic (pairwise) conversations. We examine this challenge from two viewpoints, initially using two conversation agents to generate a discourse on a certain topic with an assigned personality from the OCEAN framework (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) as High/Low for each trait. This is followed by using multiple judge agents to infer the original traits assigned to explore prediction consistency, inter-model agreement, and alignment with the assigned personality. Our findings indicate that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings. These inconsistencies emphasise the challenges in achieving stable and interpretable personality-aligned interactions in LLMs.

Amin Qasmi, Usman Naseem, Mehwish Nasim

We introduce a novel non-cooperative game to analyse opinion formation and resistance, incorporating principles from social psychology such as confirmation bias, resource constraints, and influence penalties. Our simulation features Large Language Model (LLM) agents competing to influence a population, with penalties imposed for generating messages that propagate or counter misinformation. This framework integrates resource optimisation into the agents' decision-making process. Our findings demonstrate that while higher confirmation bias strengthens opinion alignment within groups, it also exacerbates overall polarisation. Conversely, lower confirmation bias leads to fragmented opinions and limited shifts in individual beliefs. Investing heavily in a high-resource debunking strategy can initially align the population with the debunking agent, but risks rapid resource depletion and diminished long-term influence

Mehwish Nasim, Syed Muslim Gilani, Amin Qasmi et al.

This paper introduces a simulator designed for opinion dynamics researchers to model competing influences within social networks in the presence of LLM-based agents. By integrating established opinion dynamics principles with state-of-the-art LLMs, this tool enables the study of influence propagation and counter-misinformation strategies. The simulator is particularly valuable for researchers in social science, psychology, and operations research, allowing them to analyse societal phenomena without requiring extensive coding expertise. Additionally, the simulator will be openly available on GitHub, ensuring accessibility and adaptability for those who wish to extend its capabilities for their own research.

Xiaoge Zhang, Zijie Wu, Mingtao Feng et al.

Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-frequency and high-frequency components contribute differently at the same resolution. To address this, we propose FLaTEC, a frequency-aware compression model that enables the compression of a full scan with high compression ratios. Our approach introduces a frequency-aware mechanism that decouples low-frequency structures and high-frequency textures, while hybridizing latent triplanes as a compact proxy for point cloud. Specifically, we convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements. We then devise a frequency-disentangling technique that extracts compact low-frequency content while collecting high-frequency details across scales. The decoupled low-frequency and high-frequency components are stored in binary format. During decoding, full-spectrum signals are progressively recovered via a modulation block. Additionally, to compensate for the loss of 3D correlation, we introduce an efficient frequency-based attention mechanism that fosters local connectivity and outputs arbitrary resolution points. Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78\% and 94\% in BD-rate on both SemanticKITTI and Ford datasets.

Pranav Bhandari, Nicolas Fay, Sanjeevan Selvaganapathy et al.

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of the model during generation is a critical gap in the literature that needs to be fulfilled. Personality-aware LLMs hold a promising direction towards this objective. However, the relationship between these psychological constructs and their representations within LLMs remains underexplored and requires further investigation. Moreover, it is intriguing to understand and study the use of these representations to steer the models' behaviour. We propose a novel pipeline that extracts hidden state activations from transformer layers using the Big Five Personality Traits (Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism), which is a comprehensive and empirically validated framework to model human personality applies low-rank subspace discovery methods, and identifies trait-specific optimal layers across different model architectures for robust injection. The resulting personality-aligned directions are then operationalised through a flexible steering framework with dynamic layer selection, enabling precise control of trait expression in LLM outputs. Our findings reveal that personality traits occupy a low-rank shared subspace, and that these latent structures can be transformed into actionable mechanisms for effective steering through careful perturbations without impacting the fluency, variance and general capabilities, helping to bridge the gap between psychological theory and practical model alignment.

Sanjeeevan Selvaganapathy, Mehwish Nasim

We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining whether models with minimal safety alignment (uncensored) might provide more objective classification capabilities compared to their heavily-aligned (censored) counterparts. While uncensored models theoretically offer a less constrained perspective free from moral guardrails that could bias classification decisions, our results reveal a surprising trade-off: censored models significantly outperform their uncensored counterparts in both accuracy and robustness, achieving 78.7% versus 64.1% strict accuracy. However, this enhanced performance comes with its own limitation -- the safety alignment acts as a strong ideological anchor, making censored models resistant to persona-based influence, while uncensored models prove highly malleable to ideological framing. Furthermore, we identify critical failures across all models in understanding nuanced language such as irony. We also find alarming fairness disparities in performance across different targeted groups and systemic overconfidence that renders self-reported certainty unreliable. These findings challenge the notion of LLMs as objective arbiters and highlight the need for more sophisticated auditing frameworks that account for fairness, calibration, and ideological consistency.

Weijia Liu, Jiuxin Cao, Bo Miao et al.

Current text-driven Video Moment Retrieval (VMR) methods encode all video clips, including irrelevant ones, disrupting multimodal alignment and hindering optimization. To this end, we propose a denoise-then-retrieve paradigm that explicitly filters text-irrelevant clips from videos and then retrieves the target moment using purified multimodal representations. Following this paradigm, we introduce the Denoise-then-Retrieve Network (DRNet), comprising Text-Conditioned Denoising (TCD) and Text-Reconstruction Feedback (TRF) modules. TCD integrates cross-attention and structured state space blocks to dynamically identify noisy clips and produce a noise mask to purify multimodal video representations. TRF further distills a single query embedding from purified video representations and aligns it with the text embedding, serving as auxiliary supervision for denoising during training. Finally, we perform conditional retrieval using text embeddings on purified video representations for accurate VMR. Experiments on Charades-STA and QVHighlights demonstrate that our approach surpasses state-of-the-art methods on all metrics. Furthermore, our denoise-then-retrieve paradigm is adaptable and can be seamlessly integrated into advanced VMR models to boost performance.

Xiaoge Zhang, Zijie Wu, Mehwish Nasim et al.

Lossy compression relies on an autoencoder to transform a point cloud into latent points for storage, leaving the inherent redundancy of latent representations unexplored. To reduce redundancy in latent points, we propose a diffusion-based framework guided by sparse priors that achieves high reconstruction quality, especially at low bitrates. Our approach features an efficient dual-density data flow that relaxes size constraints on latent points. It hybridizes a probabilistic conditional diffusion model to encapsulate essential details for reconstruction within sparse priors, which are decoupled hierarchically into intra- and inter-point priors. Specifically, our DiffCom encodes the original point cloud into latent points and decoupled sparse priors through separate encoders. To dynamically attend to geometric and semantic cues from the priors at each encoding and decoding layer, we employ an attention-guided latent denoiser conditioned on the decoupled priors. Additionally, we integrate the local distribution into the arithmetic encoder and decoder to enhance local context modeling of the sparse points. The original point cloud is reconstructed through a point decoder. Compared to state-of-the-art methods, our approach achieves a superior rate-distortion trade-off, as evidenced by extensive evaluations on the ShapeNet dataset and standard test datasets from the MPEG PCC Group.

Liuyue Jiang, Asangi Jayatilaka, Mehwish Nasim et al.

The dynamics of cyber threats are increasingly complex, making it more challenging than ever for organizations to obtain in-depth insights into their cyber security status. Therefore, organizations rely on Cyber Situational Awareness (CSA) to support them in better understanding the threats and associated impacts of cyber events. Due to the heterogeneity and complexity of cyber security data, often with multidimensional attributes, sophisticated visualization techniques are needed to achieve CSA. However, there have been no previous attempts to systematically review and analyze the scientific literature on CSA visualizations. In this paper, we systematically select and review 54 publications that discuss visualizations to support CSA. We extract data from these papers to identify key stakeholders, information types, data sources, and visualization techniques. Furthermore, we analyze the level of CSA supported by the visualizations, alongside examining the maturity of the visualizations, challenges, and practices related to CSA visualizations to prepare a full analysis of the current state of CSA in an organizational context. Our results reveal certain gaps in CSA visualizations. For instance, the largest focus is on operational-level staff, and there is a clear lack of visualizations targeting other types of stakeholders such as managers, higher-level decision makers, and non-expert users. Most papers focus on threat information visualization, and there is a dearth of papers that visualize impact information, response plans, and information shared within teams. Based on the results that highlight the important concerns in CSA visualizations, we recommend a list of future research directions.

Ba Dung Le, Guanhua Wang, Mehwish Nasim et al.

Preventing organizations from Cyber exploits needs timely intelligence about Cyber vulnerabilities and attacks, referred as threats. Cyber threat intelligence can be extracted from various sources including social media platforms where users publish the threat information in real time. Gathering Cyber threat intelligence from social media sites is a time consuming task for security analysts that can delay timely response to emerging Cyber threats. We propose a framework for automatically gathering Cyber threat intelligence from Twitter by using a novelty detection model. Our model learns the features of Cyber threat intelligence from the threat descriptions published in public repositories such as Common Vulnerabilities and Exposures (CVE) and classifies a new unseen tweet as either normal or anomalous to Cyber threat intelligence. We evaluate our framework using a purpose-built data set of tweets from 50 influential Cyber security related accounts over twelve months (in 2018). Our classifier achieves the F1-score of 0.643 for classifying Cyber threat tweets and outperforms several baselines including binary classification models. Our analysis of the classification results suggests that Cyber threat relevant tweets on Twitter do not often include the CVE identifier of the related threats. Hence, it would be valuable to collect these tweets and associate them with the related CVE identifier for cyber security applications.

Jonathan Tuke, Andrew Nguyen, Mehwish Nasim et al.

The combination of large open data sources with machine learning approaches presents a potentially powerful way to predict events such as protest or social unrest. However, accounting for uncertainty in such models, particularly when using diverse, unstructured datasets such as social media, is essential to guarantee the appropriate use of such methods. Here we develop a Bayesian method for predicting social unrest events in Australia using social media data. This method uses machine learning methods to classify individual postings to social media as being relevant, and an empirical Bayesian approach to calculate posterior event probabilities. We use the method to predict events in Australian cities over a period in 2017/18.