We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Evaluating WMT 2024 Metrics Shared Task Submissions on AfriMTE (the African Challenge Set)
Large Language Models (LLMs) have shown significant promise in various tasks, including identifying the political beliefs of English-speakin… (see more)g social media users from their posts. However, assessing LLMs for this task in non-English languages remains unexplored. In this work, we ask to what extent LLMs can predict the political ideologies of users in Persian social media. To answer this question, we first acknowledge that political parties are not well-defined among Persian users, and therefore, we simplify the task to a much simpler task of hyperpartisan ideology detection. We create a new benchmark and show the potential and limitations of both open-source and commercial LLMs in classifying the hyper-partisan ideologies of users. We compare these models with smaller fine-tuned models, both on the Persian language (ParsBERT) and translated data (RoBERTa), showing that they considerably outperform generative LLMs in this task. We further demonstrate that the performance of the generative LLMs degrades when classifying users based on their tweets instead of their bios and even when tweets are added as additional information, whereas the smaller fine-tuned models are robust and achieve similar performance for all classes. This study is a first step toward political ideology detection in Persian Twitter, with implications for future research to understand the dynamics of ideologies in Persian social media.
Large Language Models (LLMs) have shown significant promise in various tasks, including identifying the political beliefs of English-speakin… (see more)g social media users from their posts. However, assessing LLMs for this task in non-English languages remains unexplored. In this work, we ask to what extent LLMs can predict the political ideologies of users in Persian social media. To answer this question, we first acknowledge that political parties are not well-defined among Persian users, and therefore, we simplify the task to a much simpler task of hyperpartisan ideology detection. We create a new benchmark and show the potential and limitations of both open-source and commercial LLMs in classifying the hyper-partisan ideologies of users. We compare these models with smaller fine-tuned models, both on the Persian language (ParsBERT) and translated data (RoBERTa), showing that they considerably outperform generative LLMs in this task. We further demonstrate that the performance of the generative LLMs degrades when classifying users based on their tweets instead of their bios and even when tweets are added as additional information, whereas the smaller fine-tuned models are robust and achieve similar performance for all classes. This study is a first step toward political ideology detection in Persian Twitter, with implications for future research to understand the dynamics of ideologies in Persian social media.
An Exact Method for (Constrained) Assortment Optimization Problems with Product Costs
The most widely used LLMs like GPT4 and Llama 2 are trained on large amounts of data, mostly in English but are still able to deal with non-… (see more)English languages. This English bias leads to lower performance in other languages, especially low-resource ones. This paper studies the linguistic quality of LLMs in two non-English high-resource languages: Dutch and French, with a focus on the influence of English. We first construct a comparable corpus of text generated by humans versus LLMs (GPT-4, Zephyr, and GEITje) in the news domain. We proceed to annotate linguistic issues in the LLM-generated texts, obtaining high inter-annotator agreement, and analyse these annotated issues. We find a substantial influence of English for all models under all conditions: on average, 16% of all annotations of linguistic errors or peculiarities had a clear link to English. Fine-tuning a LLM to a target language (GEITje is fine-tuned on Dutch) reduces the number of linguistic issues and probably also the influence of English. We further find that using a more elaborate prompt leads to linguistically better results than a concise prompt. Finally, increasing the temperature for one of the models leads to lower linguistic quality but does not alter the influence of English.
The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has p… (see more)roven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its effects on model efficiency, stability, and performance during training. By offering a comprehensive recipe of effective quantization strategies to be applied during the pre-training of Transformers, we promote high training efficiency from scratch while retaining language modeling ability. Code is available at https://github.com/chandar-lab/EfficientLLMs.
Language model capabilities predictably improve from scaling the model’s size and training data. Motivated by this, increasingly large lan… (see more)guage models have been trained, yielding an array of impressive capabilities. Yet these models suffer from adversarial prompts such as “jailbreaks” that hijack models to perform undesired behavior, posing a significant risk of misuse. Prior work has found that computer vision models become more robust with model and data scaling, raising the question: does language model robustness also improve with scale? We study this question empirically, finding that larger models respond substantially more effectively to adversarial training, but there is little to no benefit from model scale in the absence of defenses.
Introduction Mobile health apps risk widening health disparities if they overlook digital inclusion. The digital divide, encompassing access… (see more), familiarity, and readiness, poses a significant barrier to medical interventions. Existing literature lacks exploration of the digital divide's contributing factors. Hence, data are needed to comprehend the challenges in developing inclusive health apps. Methods We created a survey to gauge internet and smartphone access, smartphone familiarity, and readiness for using mobile health apps among caregivers of pediatric patients in tertiary care. Open-ended questions solicited feedback and suggestions on mobile health applications. Responses were categorized by similarity and compared. Developed with patient partners, the survey underwent cognitive testing and piloting for accuracy. Results Data from 209 respondents showed that 23% were affected by the digital divide, mainly due to unfamiliarity with digital skills. Among 49 short text responses about health app concerns, 31 mentioned security and confidentiality, with 7 mentioning the impersonal nature of such apps. Desired features included messaging healthcare providers, scheduling, task reminders, and simplicity. Conclusions This study underscores a digital divide among caregivers of pediatric patients, with nearly a quarter affected primarily due to a lack of digital comfort. Respondents emphasized user-friendliness and online security for health apps. Future apps should prioritize digital inclusion by addressing the significant barriers and carefully considering patient and family concerns.
In offline model-based optimisation (MBO) we are interested in using machine learning to de-sign candidates that maximise some measure of d… (see more)esirability through an expensive but real-world scoring process. Offline MBO tries to approximate this expensive scoring function and use that to evaluate generated designs, however evaluation is non-exact because one approximation is being evaluated with another. Instead, we ask ourselves: if we did have the real world scoring function at hand, what cheap-to-compute validation metrics would correlate best with this? Since the real-world scoring function is available for simulated MBO datasets, insights obtained from this can be transferred over to real-world offline MBO tasks where the real-world scoring function is expensive to compute. To address this, we propose a conceptual evaluation framework that is amenable to measuring extrapolation, and apply this to conditional denoising diffusion models. Empirically, we find that two validation metrics – agreement and Frechet distance – correlate quite well with the ground truth. When there is high variability in conditional generation, feedback is required in the form of an approximated version of the real-world scoring function. Furthermore, we find that generating high-scoring samples may require heavily weighting the generative model in favour of sample quality, potentially at the cost of sample diversity.
