Liam D. Turner

Zara Siddique, Liam D. Turner, Luis Espinosa-Anke

Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand the effect of these stereotypes more comprehensively, we introduce GlobalBias, a dataset of 876k sentences incorporating 40 distinct gender-by-ethnicity groups alongside descriptors typically used in bias literature, which enables us to study a broad set of stereotypes from around the world. We use GlobalBias to directly probe a suite of LMs via perplexity, which we use as a proxy to determine how certain stereotypes are represented in the model's internal representations. Following this, we generate character profiles based on given names and evaluate the prevalence of stereotypes in model outputs. We find that the demographic groups associated with various stereotypes remain consistent across model likelihoods and model outputs. Furthermore, larger models consistently display higher levels of stereotypical outputs, even when explicitly instructed not to.

Zara Siddique, Liam D. Turner, Luis Espinosa-Anke

We introduce Dialz, a framework for advancing research on steering vectors for open-source LLMs, implemented in Python. Steering vectors allow users to modify activations at inference time to amplify or weaken a 'concept', e.g. honesty or positivity, providing a more powerful alternative to prompting or fine-tuning. Dialz supports a diverse set of tasks, including creating contrastive pair datasets, computing and applying steering vectors, and visualizations. Unlike existing libraries, Dialz emphasizes modularity and usability, enabling both rapid prototyping and in-depth analysis. We demonstrate how Dialz can be used to reduce harmful outputs such as stereotypes, while also providing insights into model behaviour across different layers. We release Dialz with full documentation, tutorials, and support for popular open-source models to encourage further research in safe and controllable language generation. Dialz enables faster research cycles and facilitates insights into model interpretability, paving the way for safer, more transparent, and more reliable AI systems.

Thomas Greatrix, Roger Whitaker, Liam Turner et al.

The potential for Large Language Models (LLMs) to generate new information offers a potential step change for research and innovation. This is challenging to assert as it can be difficult to determine what an LLM has previously seen during training, making "newness" difficult to substantiate. In this paper we observe that LLMs are able to perform sophisticated reasoning on problems with a spatial dimension, that they are unlikely to have previously directly encountered. While not perfect, this points to a significant level of understanding that state-of-the-art LLMs can now achieve, supporting the proposition that LLMs are able to yield significant emergent properties. In particular, Claude 3 is found to perform well in this regard.

Kun Tu, Jian Li, Don Towsley et al.

Networks are fundamental to the study of complex systems, ranging from social contacts, message transactions, to biological regulations and economical networks. In many realistic applications, these networks may vary over time. Modeling and analyzing such temporal properties is of additional interest as it can provide a richer characterization of relations between nodes in networks. In this paper, we explore the role of \emph{graphlets} in network classification for both static and temporal networks. Graphlets are small non-isomorphic induced subgraphs representing connected patterns in a network and their frequency can be used to assess network structures. We show that graphlet features, which are not captured by state-of-the-art methods, play a significant role in enhancing the performance of network classification. To that end, we propose two novel graphlet-based techniques, \emph{gl2vec} for network embedding, and \emph{gl-DCNN} for diffusion-convolutional neural networks. We demonstrate the efficacy and usability of \emph{gl2vec} and \emph{gl-DCNN} through extensive experiments using several real-world static and temporal networks. We find that features learned from graphlets can bring notable performance increases to state-of-the-art methods in network analysis.

Kun Tu, Jian Li, Don Towsley et al.

Network classification has a variety of applications, such as detecting communities within networks and finding similarities between those representing different aspects of the real world. However, most existing work in this area focus on examining static undirected networks without considering directed edges or temporality. In this paper, we propose a new methodology that utilizes feature representation for network classification based on the temporal motif distribution of the network and a null model for comparing against random graphs. Experimental results show that our method improves accuracy by up $10\%$ compared to the state-of-the-art embedding method in network classification, for tasks such as classifying network type, identifying communities in email exchange network, and identifying users given their app-switching behaviors.