Machine translation (MT) models are known to suffer from gender bias, especially when translating into languages with extensive gendered morphology. Accordingly, they still fall short in using gender-inclusive language, also representative of non-binary identities. In this paper, we look at gender-inclusive neomorphemes, neologistic elements that avoid binary gender markings as an approach towards fairer MT. In this direction, we explore prompting techniques with large language models (LLMs) to translate from English into Italian using neomorphemes. So far, this area has been under-explored due to its novelty and the lack of publicly available evaluation resources. We fill this gap by releasing Neo-GATE, a resource designed to evaluate gender-inclusive en-it translation with neomorphemes. With Neo-GATE, we assess four LLMs of different families and sizes and different prompt formats, identifying strengths and weaknesses of each on this novel task for MT.

Compositionality in language models presents a problem when processing idiomatic expressions, as their meaning often cannot be directly derived from their individual parts. Although fine-tuning and other optimization strategies can be used to improve representations of idiomatic expressions, this depends on the availability of relevant data. We present the Noun Compound Synonym Substitution in Books - NCSSB - datasets, which are created by substitution of synonyms of potentially idiomatic English noun compounds in public domain book texts. We explore the trade-off between data quantity and quality when training models for idiomaticity detection, in conjunction with contextual information obtained locally (from the surrounding sentences) or externally (through language resources). Performance on an idiomaticity detection task indicates that dataset quality is a stronger factor for context-enriched models, but that quantity also plays a role in models without context inclusion strategies.

Transformer-based long context generative models power emerging AI applications like hour-long video understanding and project-level coding agent. Deploying long context transformers (e.g., 100K to 10M tokens) is prohibitively expensive compared to short context (e.g., 4K tokens) model variants. Reducing the cost of long-context transformers is becoming a pressing research and engineering challenge starting from the year of 2024. This work describes a concurrent programming framework for quantitatively analyzing the efficiency challenges in serving multiple long-context requests under limited size of GPU high-bandwidth memory (HBM) regime. We give a detailed analysis of how all additional computational costs, compared to 4K context, trace back to \textit{one single source: the large size of the KV cache}. We use a 34B GPT-3.5 level model of 50K context on A100 NVLink as a running example, and describe how its large KV cache causes four types of deployment challenges: (1) prefilling long inputs takes much longer compute time and GPU memory than short inputs; (2) after prefilling, the large KV cache residing on the GPU HBM substantially restricts the number of concurrent users being served; (3) during decoding, repeatedly reading the KV cache from HBM to SM largely increases latency; (4) when KV cache memory overflows, swapping it from HBM to DDR causes significant context switching latency. We use this framework to analyze existing works and identify possibilities of combining them to build end-to-end systems. Overall, this work offers a foundational framework for analyzing long context transformer deployment and identifies directions towards reducing the inference cost of 1M context to be as cheap as 4K.

We introduce an interpretable-by-design method, optimized model-analog, that integrates deep learning with model-analog forecasting, a straightforward yet effective approach that generates forecasts from similar initial climate states in a repository of model simulations. This hybrid framework employs a convolutional neural network to estimate state-dependent weights to identify initial analog states that lead to shadowing target trajectories. The advantage of our method lies in its inherent interpretability, offering insights into initial-error-sensitive regions through estimated weights and the ability to trace the physically-based evolution of the system through analog forecasting. We evaluate our approach using the Community Earth System Model Version 2 Large Ensemble to forecast the El Ni\~no-Southern Oscillation (ENSO) on a seasonal-to-annual time scale. Results show a 10% improvement in forecasting equatorial Pacific sea surface temperature anomalies at 9-12 months leads compared to the original (unweighted) model-analog technique. Furthermore, our model demonstrates improvements in boreal winter and spring initialization when evaluated against a reanalysis dataset. Our approach reveals state-dependent regional sensitivity linked to various seasonally varying physical processes, including the Pacific Meridional Modes, equatorial recharge oscillator, and stochastic wind forcing. Additionally, disparities emerge in the sensitivity associated with El Ni\~no versus La Ni\~na events. El Ni\~no forecasts are more sensitive to initial uncertainty in tropical Pacific sea surface temperatures, while La Ni\~na forecasts are more sensitive to initial uncertainty in tropical Pacific zonal wind stress. This approach has broad implications for forecasting diverse climate phenomena, including regional temperature and precipitation, which are challenging for the original model-analog approach.

The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 Million unique text-to-Video Prompts from real users. Additionally, this dataset includes 6.69 million videos generated by four state-of-the-art diffusion models, alongside some related data. We initially discuss the curation of this large-scale dataset, a process that is both time-consuming and costly. Subsequently, we underscore the need for a new prompt dataset specifically designed for text-to-video generation by illustrating how VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Our extensive and diverse dataset also opens up many exciting new research areas. For instance, we suggest exploring text-to-video prompt engineering, efficient video generation, and video copy detection for diffusion models to develop better, more efficient, and safer models. The project (including the collected dataset VidProM and related code) is publicly available at https://vidprom.github.io under the CC-BY-NC 4.0 License.

In recent years, there has been a lot of research in artificial intelligence, focusing on leveraging argumentation theory for non-monotonic reasoning [1, 2]. Starting with Dung's seminal work [3], many researchers have considered abstract argumentation frameworks, composed of a set of arguments and a binary attack relation between them, and created many semantics for tasks such as computing accepted sets of arguments [4, 5] or rank arguments [6, 7, 8]. This abstract argumentation framework was extended with many features such as supports [9, 10, 11], sets of attacking arguments [12, 13], or probabilities [14] among others. However, one important question that remained was: "Where do argumentation frameworks come from in real-life settings?". While there are some pieces of evidence that the fundamental aspects of abstract argumentation frameworks have links with human reasoning [15, 16], humans debates or natural language texts are not always written as arguments and the relation between arguments is not always clear, even for experts [17]. The question of the origin of argumentation frameworks is crucial to facilitate the application of argumentation theory semantics in real-world contexts.

In contrast to classic software development, neural networks are crafted via a long process of trial and error that terminates when their predictive performance reaches a satisfactory level [4, 36]. The iterative and performance-driven nature of this process leaves neural networks vulnerable on many fronts [23]: poor performance on out-of-distribution [21] and adversarial inputs [32], misspecification of the neural architecture and training process [24], invocation of broken and deprecated libraries [30], outright software bugs [22]. Unfortunately, many of these vulnerabilities are not easy to catch early in the development process and may remain hidden until after deployment. Although efforts to debug the actual implementation of neural networks exist, they are based on automatic testing and thus cannot prove correctness for all inputs [33, 22, 18]. This lack of guarantees is especially concerning for safety-critical systems since common software vulnerabilities [11] (e.g., arithmetic overflows, invalid memory accesses) can make the networks produce wrong results, expose sensitive data or corrupt the system they are executed on. In this report, we tackle the challenge of producing bug-free implementations of neural networks in the following way. First, we employ software verifiers to ensure full coverage of the state space. In the past, it has been claimed that software verifiers struggle to cope with neural network code due to its size, complexity and the presence of numerous calls to the standard mathematical library [26].

We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We propose a novel foundation for OAL tasks based on partial monitoring, a theoretical framework specialized in online learning from partially informative actions. We show that previously studied binary and multi-class OAL tasks are instances of partial monitoring. We expand the real-world potential of OAL by introducing a new class of cost-sensitive OAL tasks. We propose NeuralCBP, the first PM strategy that accounts for predictive uncertainty with deep neural networks. Our extensive empirical evaluation on open source datasets shows that NeuralCBP has favorable performance against state-of-the-art baselines on multiple binary, multi-class and cost-sensitive OAL tasks.

Large language models (LLMs) with retrieval augmented-generation (RAG) have been the optimal choice for scalable generative AI solutions in the recent past. However, the choice of use-cases that incorporate RAG with LLMs have been either generic or extremely domain specific, thereby questioning the scalability and generalizability of RAG-LLM approaches. In this work, we propose a unique LLM-based system where multiple LLMs can be invoked to enable data authentication, user query routing, data retrieval and custom prompting for question answering capabilities from data tables that are highly varying and large in size. Our system is tuned to extract information from Enterprise-level data products and furnish real time responses under 10 seconds. One prompt manages user-to-data authentication followed by three prompts to route, fetch data and generate a customizable prompt natural language responses. Additionally, we propose a five metric scoring module that detects and reports hallucinations in the LLM responses. Our proposed system and scoring metrics achieve >90% confidence scores across hundreds of user queries in the sustainability, financial health and social media domains. Extensions to the proposed extreme RAG architectures can enable heterogeneous source querying using LLMs.

Just one week before the world's second-ever global summit on artificial intelligence, protesters of a small but growing movement called "Pause AI" demanded that the world's governments regulate AI companies and freeze the development of new cutting edge artificial intelligence models. They say that the development of these models should only be allowed to continue if companies agree to let them be thoroughly evaluated to test their safety first. Protests took place across thirteen different countries, including the U.S., the U.K, Brazil, Germany, Australia, and Norway on Monday. In London, a group of 20 or so protesters stood outside of the U.K.'s Department of Science, Innovation and Technology chanting things like "stop the race, it's not safe" and "who's future? The protestors say their goal is to get governments to regulate the companies developing frontier AI models, including OpenAI's Chat GPT. They say that companies are not taking enough precautions to make sure their AI models are safe enough to be released into the world. "[AI companies] have proven time and time again… through the way that these companies' workers are treated, with the way that they treat other people's work by literally stealing it and throwing it into their models, They have proven that they cannot be trusted," said Gideon Futerman, an Oxford undergraduate student who gave a speech at the protest. One protester, Tara Steele, a freelance writer who works on blogs and SEO content, said that she had seen the technology impact her own livelihood. "I have noticed since ChatGPT came out, the demand for freelance work has reduced dramatically," she says. "I love writing personally… I've really loved it.