Automatic extraction of party (dis)similarities from texts such as party election manifestos or parliamentary speeches plays an increasing role in computational political science. However, existing approaches are fundamentally limited to targeting only global party (dis)-similarity: they condense the relationship between a pair of parties into a single figure, their similarity. In aggregating over all policy domains (e.g., health or foreign policy), they do not provide any qualitative insights into which domains parties agree or disagree on. This paper proposes a workflow for estimating policy domain aware party similarity that overcomes this limitation. The workflow covers (a) definition of suitable policy domains; (b) automatic labeling of domains, if no manual labels are available; (c) computation of domain-level similarities and aggregation at a global level; (d) extraction of interpretable party positions on major policy axes via multidimensional scaling. We evaluate our workflow on manifestos from the German federal elections. We find that our method (a) yields high correlation when predicting party similarity at a global level and (b) provides accurate party-specific positions, even with automatically labelled policy domains.

Across domains such as medicine, employment, and criminal justice, predictive models often target labels that imperfectly reflect the outcomes of interest to experts and policymakers. For example, clinical risk assessments deployed to inform physician decision-making often predict measures of healthcare utilization (e.g., costs, hospitalization) as a proxy for patient medical need. These proxies can be subject to outcome measurement error when they systematically differ from the target outcome they are intended to measure. However, prior modeling efforts to characterize and mitigate outcome measurement error overlook the fact that the decision being informed by a model often serves as a risk-mitigating intervention that impacts the target outcome of interest and its recorded proxy. Thus, in these settings, addressing measurement error requires counterfactual modeling of treatment effects on outcomes. In this work, we study intersectional threats to model reliability introduced by outcome measurement error, treatment effects, and selection bias from historical decision-making policies. We develop an unbiased risk minimization method which, given knowledge of proxy measurement error properties, corrects for the combined effects of these challenges. We also develop a method for estimating treatment-dependent measurement error parameters when these are unknown in advance. We demonstrate the utility of our approach theoretically and via experiments on real-world data from randomized controlled trials conducted in healthcare and employment domains. As importantly, we demonstrate that models correcting for outcome measurement error or treatment effects alone suffer from considerable reliability limitations. Our work underscores the importance of considering intersectional threats to model validity during the design and evaluation of predictive models for decision support.

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen attacks. Still, the limited certified robustness that is currently achievable has been a bottleneck for their practical adoption. Gowal et al. and Wang et al. have shown that generating additional training data using state-of-the-art diffusion models can considerably improve the robustness of adversarial training. In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses. In addition, we provide a list of recommendations to scale the robustness of certified training approaches. One of our main insights is that the generalization gap, i.e., the difference between the training and test accuracy of the original model, is a good predictor of the magnitude of the robustness improvement when using additional generated data. Our approach achieves state-of-the-art deterministic robustness certificates on CIFAR-10 for the $\ell_2$ ($\epsilon = 36/255$) and $\ell_\infty$ ($\epsilon = 8/255$) threat models, outperforming the previous best results by $+3.95\%$ and $+1.39\%$, respectively. Furthermore, we report similar improvements for CIFAR-100.

Identifying, classifying, and analyzing arguments in legal discourse has been a prominent area of research since the inception of the argument mining field. However, there has been a major discrepancy between the way natural language processing (NLP) researchers model and annotate arguments in court decisions and the way legal experts understand and analyze legal argumentation. While computational approaches typically simplify arguments into generic premises and claims, arguments in legal research usually exhibit a rich typology that is important for gaining insights into the particular case and applications of law in general. We address this problem and make several substantial contributions to move the field forward. First, we design a new annotation scheme for legal arguments in proceedings of the European Court of Human Rights (ECHR) that is deeply rooted in the theory and practice of legal argumentation research. Second, we compile and annotate a large corpus of 373 court decisions (2.3M tokens and 15k annotated argument spans). Finally, we train an argument mining model that outperforms state-of-the-art models in the legal NLP domain and provide a thorough expert-based evaluation. All datasets and source codes are available under open lincenses at https://github.com/trusthlt/mining-legal-arguments.

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream training data for finetuning. Often in real-world situations, there is a scarcity of data available for finetuning, falling somewhere between few shot inference and fully supervised finetuning. In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks by estimating the minimal downstream training data required by them to perform transfer learning and match the performance of state-of-the-art (SOTA) supervised models. We conduct experiments on 119 tasks from Super Natural Instructions (SuperNI) in both the single task learning (STL) and multi task learning (MTL) settings. Our findings reveal that, in the STL setting, instruction tuned models equipped with 25% of the downstream train data surpass the SOTA performance on the downstream tasks. In the MTL setting, an instruction tuned model trained on only 6% of downstream training data achieve SOTA, while using 100% of the training data results in a 3.69% points improvement (ROUGE-L 74.68) over the previous SOTA. We conduct an analysis on T5 vs Tk-Instruct by developing several baselines to demonstrate that instruction tuning aids in increasing both sample efficiency and transfer learning. Additionally, we observe a consistent ~4% performance increase in both settings when pre-finetuning is performed with instructions. Finally, we conduct a categorical study and find that contrary to previous results, tasks in the question rewriting and title generation categories suffer from instruction tuning.

Two performance criteria are commonly used for infinitehorizon MDPs: 1) the discounted-reward setting, where Robust Markov decision processes (MDPs) address the reward is discounted exponentially with time; and 2) the challenge of model uncertainty by optimizing the average-reward setting, where the long-term averagereward the worst-case performance over an uncertainty over time is of interest. For systems that operate for set of MDPs. In this paper, we focus on the an extended period of time, e.g., queue control, inventory robust average-reward MDPs under the modelfree management in supply chains, or communication networks, setting. We first theoretically characterize it is more important to optimize the average-reward since the structure of solutions to the robust averagereward policies obtained from the discounted-reward setting may Bellman equation, which is essential for be myopic and have poor long-term performance (Kazemi our later convergence analysis.

OpenAI CEO Sam Altman took questions from reporters following his congressional hearing and defined "scary AI." OpenAI CEO Sam Altman said people should not try to "anthropomorphize" artificial intelligence and should discuss the powerful tech systems in the context of it being a "tool" and not a "creature." "I think there's a huge amount of speculation on that question," Altman told reporters Tuesday on Capitol Hill when asked how quickly AI could become "self-aware" if Congress does not regulate the technology. The line of questioning had echoes of the "Terminator" film series, in which AI brings about the apocalypse on the day it becomes "self-aware." "I think it's very important that we keep talking about this as a tool, not a creature, because it's so tempting to anthropomorphize it," he added. "I totally understand where the anxiety comes from. I think it's the wrong frame … the wrong way to think about it."

OpenAI CEO Sam Altman made an appeal to members of Congress under oath: Regulate artificial intelligence. Altman, whose company is on the extreme forefront of generative A.I. technology with its ChatGPT tool, testified in front of the Senate Judiciary Committee for the first time in a Tuesday hearing. And while he said he is ultimately optimistic that innovation will benefit people on a grand scale, Altman echoed his previous assertion that lawmakers should create parameters for AI creators to avoid causing "significant harm to the world." "We think it can be a printing press moment," Altman said. "We have to work together to make it so."

OpenAI CEO Sam Altman, the artificial intelligence lab behind ChatGPT, took questions from reporters following his congressional hearing, including defining "scary AI." OpenAI CEO Sam Altman outlined examples of "scary AI" to Fox News Digital after he served as a witness for a Senate subcommittee hearing on potential regulations on artificial intelligence. "Sure," Altman said when asked by Fox News Digital to provide an example of "scary AI." "An AI that could design novel biological pathogens. An AI that could hack into computer systems. I think these are all scary." "These systems can become quite powerful, which is why I was happy to be here today and why I think this is so important." Altman appeared before the Senate Judiciary Subcommittee on Privacy, Technology, and the Law on Tuesday morning to speak with lawmakers about how to best regulate the technology.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. An airstrike targeted a militant group in northern Iraq's Yazidi heartland of Sinjar on Tuesday, according to local officials, who attributed the strike to Turkey. Officials gave conflicting reports regarding the number of casualties. The semi-autonomous Kurdish region's counter-terrorism service said in a statement that three fighters were killed in the attack, and one wounded.