The task of toxicity detection is still a relevant task, especially in the context of safe and fair LMs development. Nevertheless, labeled binary toxicity classification corpora are not available for all languages, which is understandable given the resource-intensive nature of the annotation process. Ukrainian, in particular, is among the languages lacking such resources. To our knowledge, there has been no existing toxicity classification corpus in Ukrainian. In this study, we aim to fill this gap by investigating cross-lingual knowledge transfer techniques and creating labeled corpora by: (i)~translating from an English corpus, (ii)~filtering toxic samples using keywords, and (iii)~annotating with crowdsourcing. We compare LLMs prompting and other cross-lingual transfer approaches with and without fine-tuning offering insights into the most robust and efficient baselines.

The integration of Artificial Intelligence (AI) in healthcare presents a transformative potential for enhancing operational efficiency and health outcomes. Large Language Models (LLMs), such as ChatGPT, have shown their capabilities in supporting medical decision-making. Embedding LLMs in medical systems is becoming a promising trend in healthcare development. The potential of ChatGPT to address the triage problem in emergency departments has been examined, while few studies have explored its application in outpatient departments. With a focus on streamlining workflows and enhancing efficiency for outpatient triage, this study specifically aims to evaluate the consistency of responses provided by ChatGPT in outpatient guidance, including both within-version response analysis and between-version comparisons. For within-version, the results indicate that the internal response consistency for ChatGPT-4.0 is significantly higher than ChatGPT-3.5 (p=0.03) and both have a moderate consistency (71.2% for 4.0 and 59.6% for 3.5) in their top recommendation. However, the between-version consistency is relatively low (mean consistency score=1.43/3, median=1), indicating few recommendations match between the two versions. Also, only 50% top recommendations match perfectly in the comparisons. Interestingly, ChatGPT-3.5 responses are more likely to be complete than those from ChatGPT-4.0 (p=0.02), suggesting possible differences in information processing and response generation between the two versions. The findings offer insights into AI-assisted outpatient operations, while also facilitating the exploration of potentials and limitations of LLMs in healthcare utilization. Future research may focus on carefully optimizing LLMs and AI integration in healthcare systems based on ergonomic and human factors principles, precisely aligning with the specific needs of effective outpatient triage.

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various categories of data may cause its generalization performance to suffer from multi-task disturbance, and 2) the human annotation consistency rate is generally only $60\%$ to $75\%$, causing training data to contain a lot of noise. To tackle these two challenges, we introduced the idea of Mixture-of-Experts (MoE) into the field of RM for the first time. We propose the Double-Layer MoE RM (DMoERM). The outer layer MoE is a sparse model. After classifying an input into task categories, we route it to the corresponding inner layer task-specific model. The inner layer MoE is a dense model. We decompose the specific task into multiple capability dimensions and individually fine-tune a LoRA expert on each one. Their outputs are then synthesized by an MLP to compute the final rewards. To minimize costs, we call a public LLM API to obtain the capability preference labels. The validation on manually labeled datasets confirms that our model attains superior consistency with human preference and outstrips advanced generative approaches. Meanwhile, through BoN sampling and RL experiments, we demonstrate that our model outperforms state-of-the-art ensemble methods of RM and mitigates the overoptimization problem. Our code and dataset are available at: https://github.com/quanshr/DMoERM-v1.

The automated detection of conspiracy theories online typically relies on supervised learning. However, creating respective training data requires expertise, time and mental resilience, given the often harmful content. Moreover, available datasets are predominantly in English and often keyword-based, introducing a token-level bias into the models. Our work addresses the task of detecting conspiracy theories in German Telegram messages. We compare the performance of supervised fine-tuning approaches using BERT-like models with prompt-based approaches using Llama2, GPT-3.5, and GPT-4 which require little or no additional training data. We use a dataset of $\sim\!\! 4,000$ messages collected during the COVID-19 pandemic, without the use of keyword filters. Our findings demonstrate that both approaches can be leveraged effectively: For supervised fine-tuning, we report an F1 score of $\sim\!\! 0.8$ for the positive class, making our model comparable to recent models trained on keyword-focused English corpora. We demonstrate our model's adaptability to intra-domain temporal shifts, achieving F1 scores of $\sim\!\! 0.7$. Among prompting variants, the best model is GPT-4, achieving an F1 score of $\sim\!\! 0.8$ for the positive class in a zero-shot setting and equipped with a custom conspiracy theory definition.

Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network devices is not only the key to optimization and planning but also a complex goal to achieve. The primary challenges include the complexity of synchronization and load balancing between CPUs and GPUs, the variance in input data distribution, and the use of different communication devices and topologies (e.g., NVLink, PCIe, network cards) that connect multiple compute devices, coupled with the desire for flexible training configurations. Built on top of our prior work for single-GPU platforms, we address these challenges and enable multi-GPU performance modeling by incorporating (1) data-distribution-aware performance models for embedding table lookup, and (2) data movement prediction of communication collectives, into our upgraded performance modeling pipeline equipped with inter-and intra-rank synchronization for ML workloads trained on multi-GPU platforms. Beyond accurately predicting the per-iteration training time of DLRM models with random configurations with a geomean error of 5.21% on two multi-GPU platforms, our prediction pipeline generalizes well to other types of ML workloads, such as Transformer-based NLP models with a geomean error of 3.00%. Moreover, even without actually running ML workloads like DLRMs on the hardware, it is capable of generating insights such as quickly selecting the fastest embedding table sharding configuration (with a success rate of 85%).

In the rapidly evolving landscape of Natural Language Processing (NLP), Large Language Models (LLMs) have emerged as powerful tools for many tasks, such as extracting valuable insights from vast amounts of textual data. In this study, we conduct a comparative analysis of LLMs for the extraction of travel customer needs from TripAdvisor posts. Leveraging a diverse range of models, including both open-source and proprietary ones such as GPT-4 and Gemini, we aim to elucidate their strengths and weaknesses in this specialized domain. Through an evaluation process involving metrics such as BERTScore, ROUGE, and BLEU, we assess the performance of each model in accurately identifying and summarizing customer needs. Our findings highlight the efficacy of opensource LLMs, particularly Mistral 7B, in achieving comparable performance to larger closed models while offering affordability and customization benefits. Additionally, we underscore the importance of considering factors such as model size, resource requirements, and performance metrics when selecting the most suitable LLM for customer needs analysis tasks. Overall, this study contributes valuable insights for businesses seeking to leverage advanced NLP techniques to enhance customer experience and drive operational efficiency in the travel industry.

Automatic Speech Understanding (ASU) aims at human-like speech interpretation, providing nuanced intent, emotion, sentiment, and content understanding from speech and language (text) content conveyed in speech. Typically, training a robust ASU model relies heavily on acquiring large-scale, high-quality speech and associated transcriptions. However, it is often challenging to collect or use speech data for training ASU due to concerns such as privacy. To approach this setting of enabling ASU when speech (audio) modality is missing, we propose TI-ASU, using a pre-trained text-to-speech model to impute the missing speech. We report extensive experiments evaluating TI-ASU on various missing scales, both multi- and single-modality settings, and the use of LLMs. Our findings show that TI-ASU yields substantial benefits to improve ASU in scenarios where even up to 95% of training speech is missing. Moreover, we show that TI-ASU is adaptive to dropout training, improving model robustness in addressing missing speech during inference.

I'm trying to love Logitech's Signature AI Edition M750 Wireless Mouse. But I'm continually tripping over this small detail, and it literally is making me more frustrated than I should be. It's an intriguing, polarizing concept: By placing an "AI" button on the top of the mouse, Logitech gives users one-click access to ChatGPT to do one thing: simplify the writing and rewriting of text via an AI app called Logi Prompt Builder. It's a novel idea, and one you might expect Microsoft to develop, given the Copilot key that's already appearing on laptop keyboards. Instead, Logitech is leading the way.

How it works: The Trustworthy Language Model gives any output generated by a large language model a score between 0 and 1, according to its reliability. This lets people choose which responses to trust and which to throw out. Why it matters: Cleanlab hopes that its tool will make large language models more attractive to businesses worried about how much stuff they invent. But while the approach could be useful, it's unlikely to be perfect. Six weeks ago, I pre-ordered the "Firefly Petunia," a houseplant engineered with genes from bioluminescent fungi so that it glows in the dark.

Sam Altman, OpenAI's CEO, Microsoft chief Satya Nadella, Alphabet CEO Sundar Pichai are joining the government's Artificial Intelligence Safety and Security Board, according to The Wall Street Journal. They're also joined by Nvidia's Jensen Huang, Northrop Grumman's Kathy Warden and Delta's Ed Bastian, along with other leaders in the tech and AI industry. The AI board will be working with and advising the Department of Homeland Security on how it can safely deploy AI within the country's critical infrastructure. They're also tasked with conjuring recommendations for power grid operators, transportation service providers and manufacturing plants on how they can can protect their systems against potential threats that could be brought about by advances in the technology. The Biden administration ordered the creation of an AI safety board last year as part of a sweeping executive order that focuses on regulating AI development.