Explainable Artificial Intelligence (XAI) is a young but very promising field of research. Unfortunately, the progress in this field is currently slowed down by divergent and incompatible goals. We separate various threads tangled within the area of XAI into two complementary cultures of human/value-oriented explanations (BLUE XAI) and model/validation-oriented explanations (RED XAI). This position paper argues that the area of RED XAI is currently under-explored, i.e., more methods for explainability are desperately needed to question models (e.g., extract knowledge from well-performing models as well as spotting and fixing bugs in faulty models), and the area of RED XAI hides great opportunities and potential for important research necessary to ensure the safety of AI systems. We conclude this paper by presenting promising challenges in this area.

Measuring an overall autonomy score for a robotic system requires the combination of a set of relevant aspects and features of the system that might be measured in different units, qualitative, and/or discordant. In this paper, we build upon an existing non-contextual autonomy framework that measures and combines the Autonomy Level and the Component Performance of a system as overall autonomy score. We examine several methods of combining features, showing how some methods find different rankings of the same data, and we employ the weighted product method to resolve this issue. Furthermore, we introduce the non-contextual autonomy coordinate and represent the overall autonomy of a system with an autonomy distance. We apply our method to a set of seven Unmanned Aerial Systems (UAS) and obtain their absolute autonomy score as well as their relative score with respect to the best system.

We present our work on developing and training scalable graph foundation models (GFM) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFM training to tens of thousands of GPUs on datasets that consist of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as the total energy and atomic forces. Using over 150 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge National Laboratory. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier. Hyperparameter optimization (HPO) was performed on over 64,000 GPUs on Frontier to select GFM architectures with high accuracy. Early stopping was applied on each GFM architecture for energy awareness in performing such an extreme-scale task. The training of an ensemble of highest-ranked GFM architectures continued until convergence to establish uncertainty quantification (UQ) capabilities with ensemble learning. Our contribution opens the door for rapidly developing, training, and deploying GFMs using large-scale computational resources to enable AI-accelerated materials discovery and design.

The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning or adversarial testing, often yield safe outputs at the expense of contextual meaning. This can result in a diminished capacity to handle nuanced aspects of bias and toxicity, such as underrepresentation or negative portrayals across various demographics. To address these challenges, we introduce MBIAS, an LLM framework carefully instruction fine-tuned on a custom dataset designed specifically for safety interventions. MBIAS is designed to significantly reduce biases and toxic elements in LLM outputs while preserving the main information. This work also details our further use of LLMs: as annotator under human supervision and as evaluator of generated content. Empirical analysis reveals that MBIAS achieves a reduction in bias and toxicity by over 30\% in standard evaluations, and by more than 90\% in diverse demographic tests, highlighting the robustness of our approach. We make the dataset and the fine-tuned model available to the research community for further investigation and ensure reproducibility. The code for this project can be accessed here https://github.com/shainarazavi/MBIAS/tree/main. Warning: This paper contains examples that may be offensive or upsetting.

This inefficiency stems from two main facts: a focus on tail-end performance that overlooks many sampled trajectories, and the potential of gradient vanishing when the lower tail of the return distribution is overly flat. To address these challenges, we propose a simple mixture policy parameterization. This method integrates a risk-neutral policy with an adjustable policy to form a risk-averse policy. By employing this strategy, all collected trajectories can be utilized for policy updating, and the issue of vanishing gradients is counteracted by stimulating higher returns through the risk-neutral component, thus lifting the tail and preventing flatness. Our empirical study reveals that this mixture parameterization is uniquely effective across a variety of benchmark domains. Specifically, it excels in identifying risk-averse CVaR policies in some Mujoco environments where the traditional CVaR-PG fails to learn a reasonable policy.

Detecting and quantifying causality is a focal topic in the fields of science, engineering, and interdisciplinary studies. However, causal studies on non-intervention systems attract much attention but remain extremely challenging. To address this challenge, we propose a framework named Interventional Dynamical Causality (IntDC) for such non-intervention systems, along with its computational criterion, Interventional Embedding Entropy (IEE), to quantify causality. The IEE criterion theoretically and numerically enables the deciphering of IntDC solely from observational (non-interventional) time-series data, without requiring any knowledge of dynamical models or real interventions in the considered system. Demonstrations of performance showed the accuracy and robustness of IEE on benchmark simulated systems as well as real-world systems, including the neural connectomes of C. elegans, COVID-19 transmission networks in Japan, and regulatory networks surrounding key circadian genes.

Users can teach robots complex skills through Learning from Demonstration, which is automatically segmented into primitives and stored in clusters of similar skills. We propose a novel multimodal segmentation method as well as a novel trajectory clustering method. Then, when needed for reuse, we transform primitives into new environments using trajectory editing. We present simulated results for our framework with demonstrations taken on real-world robots.

Many recent language models (LMs) are capable of in-context learning (ICL), manifested in the LMs' ability to perform a new task solely from natural-language instruction. Previous work curating in-context learners assumes that ICL emerges from a vast over-parametrization or the scale of multi-task training. However, recent theoretical work attributes the ICL ability to concept-dependent training data and creates functional in-context learners even in small-scale, synthetic settings. In this work, we practically explore this newly identified axis of ICL quality. We propose Concept-aware Training (CoAT), a framework for constructing training scenarios that make it beneficial for the LM to learn to utilize the analogical reasoning concepts from demonstrations. We find that by using CoAT, pre-trained transformers can learn to better utilise new latent concepts from demonstrations and that such ability makes ICL more robust to the functional deficiencies of the previous models. Finally, we show that concept-aware in-context learning is more effective for a majority of new tasks when compared to traditional instruction tuning, resulting in a performance comparable to the previous in-context learners using magnitudes of more training data.

Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an important problem to solve, as it may violate existing copyright laws as well as the European AI Act. In this work, we propose a systematic analysis to quantify the extent of potential copyright infringements in LLMs using European law as an example. Unlike previous work, we evaluate instruction-finetuned models in a realistic end-user scenario. Our analysis builds on a proposed threshold of 160 characters, which we borrow from the German Copyright Service Provider Act and a fuzzy text matching algorithm to identify potentially copyright-infringing textual reproductions. The specificity of countermeasures against copyright infringement is analyzed by comparing model behavior on copyrighted and public domain data. We investigate what behaviors models show instead of producing protected text (such as refusal or hallucination) and provide a first legal assessment of these behaviors. We find that there are huge differences in copyright compliance, specificity, and appropriate refusal among popular LLMs. Alpaca, GPT 4, GPT 3.5, and Luminous perform best in our comparison, with OpenGPT-X, Alpaca, and Luminous producing a particularly low absolute number of potential copyright violations. Code will be published soon.

We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even benign users do. And with just a single exception (Christ and Gunn, 2024), prior works are restricted to zero-bit watermarking: machine-generated text can be detected as such, but no additional information can be extracted from the watermark. Unfortunately, merely detecting AI-generated text may not prevent future abuses. We introduce multi-user watermarks, which allow tracing model-generated text to individual users or to groups of colluding users, even in the face of adaptive prompting. We construct multi-user watermarking schemes from undetectable, adaptively robust, zero-bit watermarking schemes (and prove that the undetectable zero-bit scheme of Christ, Gunn, and Zamir (2024) is adaptively robust). Importantly, our scheme provides both zero-bit and multi-user assurances at the same time. It detects shorter snippets just as well as the original scheme, and traces longer excerpts to individuals. The main technical component is a construction of message-embedding watermarks from zero-bit watermarks. Ours is the first generic reduction between watermarking schemes for language models. A challenge for such reductions is the lack of a unified abstraction for robustness -- that marked text is detectable even after edits. We introduce a new unifying abstraction called AEB-robustness. AEB-robustness provides that the watermark is detectable whenever the edited text "approximates enough blocks" of model-generated output.