Mortgages account for the largest portion of household debt in the United States, totaling around \$12 trillion nationwide. In times of financial hardship, alleviating mortgage burdens is essential for supporting affected households. The mortgage servicing industry plays a vital role in offering this assistance, yet there has been limited research modelling the complex relationship between households and servicers. To bridge this gap, we developed an agent-based model that explores household behavior and the effectiveness of relief measures during financial distress. Our model represents households as adaptive learning agents with realistic financial attributes. These households experience exogenous income shocks, which may influence their ability to make mortgage payments. Mortgage servicers provide relief options to these households, who then choose the most suitable relief based on their unique financial circumstances and individual preferences. We analyze the impact of various external shocks and the success of different mortgage relief strategies on specific borrower subgroups. Through this analysis, we show that our model can not only replicate real-world mortgage studies but also act as a tool for conducting a broad range of what-if scenario analyses. Our approach offers fine-grained insights that can inform the development of more effective and inclusive mortgage relief solutions.

As highly automated vehicles reach higher deployment rates, they find themselves in increasingly dangerous situations. Knowing that the consequence of a crash is significant for the health of occupants, bystanders, and properties, as well as to the viability of autonomy and adjacent businesses, we must search for more efficacious ways to comprehensively and reliably train autonomous vehicles to better navigate the complex scenarios with which they struggle. We therefore introduce a taxonomy of potentially adversarial elements that may contribute to poor performance or system failures as a means of identifying and elucidating lesser-seen risks. This taxonomy may be used to characterize failures of automation, as well as to support simulation and real-world training efforts by providing a more comprehensive classification system for events resulting in disengagement, collision, or other negative consequences. This taxonomy is created from and tested against real collision events to ensure comprehensive coverage with minimal class overlap and few omissions. It is intended to be used both for the identification of harm-contributing adversarial events and in the generation thereof (to create extreme edge- and corner-case scenarios) in training procedures.

Do LMs infer the semantics of text from co-occurrence patterns in their training data? Merrill et al. (2022) argue that, in theory, probabilities predicted by an optimal LM encode semantic information about entailment relations, but it is unclear whether neural LMs trained on corpora learn entailment in this way because of strong idealizing assumptions made by Merrill et al. In this work, we investigate whether their theory can be used to decode entailment judgments from neural LMs. We find that a test similar to theirs can decode entailment relations between natural sentences, well above random chance, though not perfectly, across many datasets and LMs. This suggests LMs implicitly model aspects of semantics to predict semantic effects on sentence co-occurrence patterns. However, we find the test that predicts entailment in practice works in the opposite direction to the theoretical test. We thus revisit the assumptions underlying the original test, finding its derivation did not adequately account for redundancy in human-written text. We argue that correctly accounting for redundancy related to explanations might derive the observed flipped test and, more generally, improve linguistic theories of human speakers.

Data augmentation is an area of research which has seen active development in many machine learning fields, such as in image-based learning models, reinforcement learning for self driving vehicles, and general noise injection for point cloud data. However, convincing methods for general time series data augmentation still leaves much to be desired, especially since the methods developed for these models do not readily cross-over. Three common approaches for time series data augmentation include: (i) Constructing a physics-based model and then imbuing uncertainty over the coefficient space (for example), (ii) Adding noise to the observed data set(s), and, (iii) Having access to ample amounts of time series data sets from which a robust generative neural network model can be trained. However, for many practical problems that work with time series data in the industry: (i) One usually does not have access to a robust physical model, (ii) The addition of noise can in of itself require large or difficult assumptions (for example, what probability distribution should be used? Or, how large should the noise variance be?), and, (iii) In practice, it can be difficult to source a large representative time series data base with which to train the neural network model for the underlying problem. In this paper, we propose a methodology which attempts to simultaneously tackle all three of these previous limitations to a large extent. The method relies upon the well-studied matrix differential geometry of the Stiefel manifold, as it proposes a simple way in which time series signals can placed on, and then smoothly perturbed over the manifold. We attempt to clarify how this method works by showcasing several potential use cases which in particular work to take advantage of the unique properties of this underlying manifold.

Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted content, the current paradigm is to recruit a \textit{red team} of human testers to design input prompts (i.e., test cases) that elicit undesirable responses from LLMs. However, relying solely on human testers is expensive and time-consuming. Recent works automate red teaming by training a separate red team LLM with reinforcement learning (RL) to generate test cases that maximize the chance of eliciting undesirable responses from the target LLM. However, current RL methods are only able to generate a small number of effective test cases resulting in a low coverage of the span of prompts that elicit undesirable responses from the target LLM. To overcome this limitation, we draw a connection between the problem of increasing the coverage of generated test cases and the well-studied approach of curiosity-driven exploration that optimizes for novelty. Our method of curiosity-driven red teaming (CRT) achieves greater coverage of test cases while mantaining or increasing their effectiveness compared to existing methods. Our method, CRT successfully provokes toxic responses from LLaMA2 model that has been heavily fine-tuned using human preferences to avoid toxic outputs. Code is available at \url{https://github.com/Improbable-AI/curiosity_redteam}

Bridging the gap between diffuse x-ray or neutron scattering measurements and predicted structures derived from atom-atom pair potentials in disordered materials, has been a longstanding challenge in condensed matter physics. This perspective gives a brief overview of the traditional approaches employed over the past several decades. Namely, the use of approximate interatomic pair potentials that relate 3-dimensional structural models to the measured structure factor and its' associated pair distribution function. The use of machine learned interatomic potentials has grown in the past few years, and has been particularly successful in the cases of ionic and oxide systems. Recent advances in large scale sampling, along with a direct integration of scattering measurements into the model development, has provided improved agreement between experiments and large-scale models calculated with quantum mechanical accuracy. However, details of local polyhedral bonding and connectivity in meta-stable disordered systems still require improvement. Here we leverage MACE-MP-0; a newly introduced equivariant foundation model and validate the results against high-quality experimental scattering data for the case of molten iron(II) oxide (FeO). These preliminary results suggest that the emerging foundation model has the potential to surpass the traditional limitations of classical interatomic potentials.

The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership with Software Heritage (SWH), we build The Stack v2 on top of the digital commons of their source code archive. Alongside the SWH repositories spanning 619 programming languages, we carefully select other high-quality data sources, such as GitHub pull requests, Kaggle notebooks, and code documentation. This results in a training set that is 4x larger than the first StarCoder dataset. We train StarCoder2 models with 3B, 7B, and 15B parameters on 3.3 to 4.3 trillion tokens and thoroughly evaluate them on a comprehensive set of Code LLM benchmarks. We find that our small model, StarCoder2-3B, outperforms other Code LLMs of similar size on most benchmarks, and also outperforms StarCoderBase-15B. Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size. In addition, it matches or outperforms CodeLlama-34B, a model more than twice its size. Although DeepSeekCoder- 33B is the best-performing model at code completion for high-resource languages, we find that StarCoder2-15B outperforms it on math and code reasoning benchmarks, as well as several low-resource languages. We make the model weights available under an OpenRAIL license and ensure full transparency regarding the training data by releasing the SoftWare Heritage persistent IDentifiers (SWHIDs) of the source code data.

In this work, we formulate the problem of team formation amidst conflicts. The goal is to assign individuals to tasks, with given capacities, taking into account individuals' task preferences and the conflicts between them. Using dependent rounding schemes as our main toolbox, we provide efficient approximation algorithms. Our framework is extremely versatile and can model many different real-world scenarios as they arise in educational settings and human-resource management. We test and deploy our algorithms on real-world datasets and we show that our algorithms find assignments that are better than those found by natural baselines. In the educational setting we also show how our assignments are far better than those done manually by human experts. In the human resource management application we show how our assignments increase the diversity of teams. Finally, using a synthetic dataset we demonstrate that our algorithms scale very well in practice.

Such fine-tuning Stance detection is a fundamental computational approaches can benefit from both the general language task that is widely used across many disciplines understanding from the pre-training as well such as political science and communication studies as the problem-specific thing, even without spending (Wang et al., 2019b; Küçük and Can, 2020) Its a huge amount of computing resources (Wang goal is to extract the standpoint or stance (e.g., Favor, et al., 2022a). Against, or Neutral) towards a target from a More recently, the GPT family of models (Radford given text. Given that modern democratic societies et al., 2019; Brown et al., 2020) birthed another make societal decisions by aggregating people's explicit powerful and even simpler paradigm of incontext stances through voting, estimation of peoples' learning ("few-shot" or "zero-shot"). Instead stances is a useful task. While a representative survey of tuning any parameters of the model, it is the gold standard, it falls short in scalability simply uses the input to guide the model to produce and cost (Salganik, 2019). Surveys can also produce the desired output for downstream tasks. For biased results due to the people's tendency to instance, a few examples related to the task can be report more socially acceptable positions even in fed as the context to the LLM.

In today's digital age, characterized by rapid news consumption and increasing vulnerability to propaganda, fostering citizens' critical thinking is crucial for stable democracies. This paper introduces the design of ClarifAI, a novel automated propaganda detection tool designed to nudge readers towards more critical news consumption by activating the analytical mode of thinking, following Kahneman's dual-system theory of cognition. Using Large Language Models, ClarifAI detects propaganda in news articles and provides context-rich explanations, enhancing users' understanding and critical thinking. Our contribution is threefold: first, we propose the design of ClarifAI; second, in an online experiment, we demonstrate that this design effectively encourages news readers to engage in more critical reading; and third, we emphasize the value of explanations for fostering critical thinking. The study thus offers both a practical tool and useful design knowledge for mitigating propaganda in digital news.