The overwhelming success of OpenAI's ChatGPT, whose first version was released one year ago, has led to an undeniable surge of excitement about large language models (LLMs) among researchers and the general public alike. OpenAI's anything-but-open approach to sharing its models or information about training them, however, has led to an equally passionate reaction among those who feel that AI development should be widely accessible and that data usage should be transparent in order to protect the rights of those who have contributed the data and that data - a resource crucial to the development and understanding of AI models - should be shared with the broader research community. The call for transparency has begun to bear fruit. High-profile language models like Falcon,[Almazrouei et al., 2023] LLaMa2 [Touvron et al., 2023] and MPT [MosaicML NLP Team, 2023] - to name just a few - come very close to a classic definition of open source. A central part of OpenLLM France's mission is to contribute to this momentum by building language models and remaining fully transparent about every step of model training, including the data used for training. Another objective, which we find equally important, is to increase the availability of language models and training data geared to languages other than English and to non-anglophone cultures. Indeed, the majority of the high-profile LLMs available today are trained primarily on English documents coming from anglophone cultures. Only 0.16% of the data used to train LLaMa2 comes from French, for example.

Machine translation (MT) is routinely evaluated using various segment-level similarity metrics against one or more reference translations. At the same time, reference translations acquired in the standard way are often criticized for their flaws of various types. For several high-resourced language pairs, MT quality reaches levels comparable to the quality of the reference translation (Freitag et al. 2022; Hassan et al. 2018) and sometimes MT even significantly surpasses humans in a particular evaluation setting (Popel et al. 2020). Given this, one could conclude that state-of-the-art MT has reached the point where reference-based evaluation is no longer reliable and we have to resort to other methods (such as targeted expert evaluation of particular outputs), even if they are costly, subjective and possibly impossible to automate. The narrow goal of the presented work is to allow for an "extension of the expiry date" for reference-based evaluation methods. In a broader perspective, we want to formulate a methodology for creating reference translations which avoid the often-observed deficiencies of "standard" or "professional" reference translations, be it multiple interfering phenomena, inappropriate expressions, ignorance of topic-focus articulation (information structure) or other abundant shortcomings in the translation, indicating their authors' insensitivity to the topic itself, but above all to the source and target language. To this end, we introduce so-called optimal reference translations (ORT), which are intended to represent optimal (ideal or excellent) human translations (should they be the subject of a translation quality evaluation).

Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans. Previous results show that modeling human behavior can significantly improve the performance of the algorithms. However, modeling humans correctly is a complex problem, and the models are often simplified and assume humans make mistakes according to some distribution or train parameters for the whole population from which they sample. In this work, we use data gathered by psychologists who identified personality types that increase the likelihood of performing malicious acts. However, in the previous work, the tests on a handmade game could not show strategic differences between the models. We created a novel model that links its parameters to psychological traits. We optimized over parametrized games and created games in which the differences are profound. Our work can help with automatic game generation when we need a game in which some models will behave differently and to identify situations in which the models do not align.

Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has proposed various methods to comprehend the decision-making processes of opaque DNNs. However, only few XAI methods are suitable of ensuring safety in practice as they heavily rely on repeated labor-intensive and possibly biased human assessment. In this work, we present a novel post-hoc concept-based XAI framework that conveys besides instance-wise (local) also class-wise (global) decision-making strategies via prototypes. What sets our approach apart is the combination of local and global strategies, enabling a clearer understanding of the (dis-)similarities in model decisions compared to the expected (prototypical) concept use, ultimately reducing the dependence on human long-term assessment. Quantifying the deviation from prototypical behavior not only allows to associate predictions with specific model sub-strategies but also to detect outlier behavior. As such, our approach constitutes an intuitive and explainable tool for model validation. We demonstrate the effectiveness of our approach in identifying out-of-distribution samples, spurious model behavior and data quality issues across three datasets (ImageNet, CUB-200, and CIFAR-10) utilizing VGG, ResNet, and EfficientNet architectures. Code is available on https://github.com/maxdreyer/pcx.

We use GPT-4 to obtain position estimates of political texts in continuous spaces. We develop and validate a new approach by positioning British party manifestos on the economic, social, and immigration policy dimensions and tweets by members of the US Congress on the left-right ideological spectrum. For the party manifestos, the correlation between the positions produced by GPT-4 and experts is 93% or higher, a performance similar to or better than that obtained with crowdsourced position estimates. For individual tweets, the positions obtained with GPT-4 achieve a correlation of 91% with crowdsourced position estimates. For senators of the 117th US Congress, the positions obtained with GPT-4 achieve a correlation of 97% with estimates based on roll call votes and of 96% with those based on campaign funding. Correlations are also substantial within party, indicating that position estimates produced with GPT-4 capture within-party differences between senators. Overall, using GPT-4 for ideological scaling is fast, cost-efficient, and reliable. This approach provides a viable alternative to scaling by both expert raters and crowdsourcing.

Traditionally, social choice theory has only been applicable to choices among a few predetermined alternatives but not to more complex decisions such as collectively selecting a textual statement. We introduce generative social choice, a framework that combines the mathematical rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. This framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies rigorous representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We apply this framework to the problem of generating a slate of statements that is representative of opinions expressed as free-form text; specifically, we develop a democratic process with representation guarantees and use this process to represent the opinions of participants in a survey about chatbot personalization. We find that 93 out of 100 participants feel "mostly" or "perfectly" represented by the slate of five statements we extracted.

Cyberattacks are increasingly threatening networked systems, often with the emergence of new types of unknown (zero-day) attacks and the rise of vulnerable devices. Such attacks can also target multiple components of a Supply Chain, which can be protected via Machine Learning (ML)-based Intrusion Detection Systems (IDSs). However, the need to learn large amounts of labelled data often limits the applicability of ML-based IDSs to cybersystems that only have access to private local data, while distributed systems such as Supply Chains have multiple components, each of which must preserve its private data while being targeted by the same attack To address this issue, this paper proposes a novel Decentralized and Online Federated Learning Intrusion Detection (DOF-ID) architecture based on the G-Network model with collaborative learning, that allows each IDS used by a specific component to learn from the experience gained in other components, in addition to its own local data, without violating the data privacy of other components. The performance evaluation results using public Kitsune and Bot-IoT datasets show that DOF-ID significantly improves the intrusion detection performance in all of the collaborating components, with acceptable computation time for online learning.

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts. While there have been approaches for NLP tasks that require comparative reasoning, they suffer from costly manual data labeling and limited generalizability to different tasks. Our approach introduces a novel method of collecting scalable data for text-based entity comparison, which leverages both structured and unstructured data. Moreover, we present a framework of pre-training language models via three novel objectives on comparative reasoning. Evaluation on downstream tasks including comparative question answering, question generation, and summarization shows that our pre-training framework significantly improves the comparative reasoning abilities of language models, especially under low-resource conditions. This work also releases the first integrated benchmark for comparative reasoning.

Algorithmic fairness is of utmost societal importance, yet the current trend in large-scale machine learning models requires training with massive datasets that are frequently biased. In this context, pre-processing methods that focus on modeling and correcting bias in the data emerge as valuable approaches. In this paper, we propose FairShap, a novel instance-level data re-weighting method for fair algorithmic decision-making through data valuation by means of Shapley Values. FairShap is model-agnostic and easily interpretable, as it measures the contribution of each training data point to a predefined fairness metric. We empirically validate FairShap on several state-of-the-art datasets of different nature, with a variety of training scenarios and models and show how it yields fairer models with similar levels of accuracy than the baselines. We illustrate FairShap's interpretability by means of histograms and latent space visualizations. Moreover, we perform a utility-fairness study, and ablation and runtime experiments to illustrate the impact of the size of the reference dataset and FairShap's computational cost depending on the size of the dataset and the number of features. We believe that FairShap represents a promising direction in interpretable and model-agnostic approaches to algorithmic fairness that yield competitive accuracy even when only biased datasets are available.

The issue of factual consistency in abstractive summarization has received extensive attention in recent years, and the evaluation of factual consistency between summary and document has become an important and urgent task. Most of the current evaluation metrics are adopted from the question answering (QA) or natural language inference (NLI) task. However, the application of QA-based metrics is extremely time-consuming in practice while NLI-based metrics are lack of interpretability. In this paper, we propose a cloze-based evaluation framework called ClozE and show the great potential of the cloze-based metric. It inherits strong interpretability from QA, while maintaining the speed of NLI- level reasoning. We demonstrate that ClozE can reduce the evaluation time by nearly 96% relative to QA-based metrics while retaining their interpretability and performance through experiments on six human-annotated datasets and a meta-evaluation benchmark GO FIGURE (Gabriel et al., 2021). Finally, we discuss three important facets of ClozE in practice, which further shows better overall performance of ClozE compared to other metrics.