The ability of Large Language Models (LLMs) to mimic human behavior triggered a plethora of computational social science research, assuming that empirical studies of humans can be conducted with AI agents instead. Since there have been conflicting research findings on whether and when this hypothesis holds, there is a need to better understand the differences in their experimental designs. We focus on replicating the behavior of social network users with the use of LLMs for the analysis of communication on social networks. First, we provide a formal framework for the simulation of social networks, before focusing on the sub-task of imitating user communication. We empirically test different approaches to imitate user behavior on X in English and German. Our findings suggest that social simulations should be validated by their empirical realism measured in the setting in which the simulation components were fitted. With this paper, we argue for more rigor when applying generative-agent-based modeling for social simulation.

As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This paper introduces a novel formal framework for categorizing and mitigating these emergent security risks by integrating adaptive, real-time monitoring, and dynamic risk mitigation strategies tailored to generative models' unique vulnerabilities. We identify previously under-explored risks, including latent space exploitation, multi-modal cross-attack vectors, and feedback-loop-induced model degradation. Our framework employs a layered approach, incorporating anomaly detection, continuous red-teaming, and real-time adversarial simulation to mitigate these risks. We focus on formal verification methods to ensure model robustness and scalability in the face of evolving threats. Though theoretical, this work sets the stage for future empirical validation by establishing a detailed methodology and metrics for evaluating the performance of risk mitigation strategies in generative AI systems.

Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches use valuable additional data for improving model correctness and aligning learned models with human priors. Meanwhile, a growing body of evidence suggests that some language models can (1) store a large amount of knowledge in their parameters, and (2) perform inference over tasks in textual inputs at test time. These results raise the possibility that, for some tasks, humans cannot explain to a model any more about the task than it already knows or could infer on its own. In this paper, we study the circumstances under which explanations of individual data points can (or cannot) improve modeling performance. In order to carefully control important properties of the data and explanations, we introduce a synthetic dataset for experiments, and we also make use of three existing datasets with explanations: e-SNLI, TACRED, and SemEval. We first give a formal framework for the available modeling approaches, in which explanation data can be used as model inputs, as targets, or as a prior. After arguing that the most promising role for explanation data is as model inputs, we propose to use a retrieval-based method and show that it solves our synthetic task with accuracies upwards of 95%, while baselines without explanation data achieve below 65% accuracy. We then identify properties of datasets for which retrieval-based modeling fails. With the three existing datasets, we find no improvements from explanation retrieval. Drawing on findings from our synthetic task, we suggest that at least one of six preconditions for successful modeling fails to hold with these datasets. Our code is publicly available at https://github.com/peterbhase/ExplanationRoles

Binary "YES-NO" notions of process compliance are not very helpful to managers for assessing the operational performance of their company because a large number of cases fall in the grey area of partial compliance. Hence, it is necessary to have ways to quantify partial compliance in terms of metrics and be able to classify actual cases by assigning a numeric value of compliance to them. In this paper, we formulate an evaluation framework to quantify the level of compliance of business processes across different levels of abstraction (such as task, trace and process level) and across multiple dimensions of each task(such as temporal, monetary, role-, data-, and quality-related) to provide managers more useful information about their operations and to help them improve their decision making processes. Our approach can also add social value by making social services provided by local, state and federal governments more flexible and improving the lives of citizens.

As robots evolve into an integral part of the human ecosystem, humans and robots will be involved in a multitude of collaborative tasks that require complex coordination and cooperation. Indeed there has been extensive work in the robotics, planning as well as the human-robot interaction communities to understand and facilitate such seamless teaming. However, it has been argued that their increased participation as independent autonomous agents in hitherto human-habited environments has introduced many new challenges to the view of traditional human-robot teaming. When robots are deployed with independent and often self-sufficient tasks in a shared workspace, teams are often not formed explicitly and multiple teams cohabiting an environment interact more like colleagues rather than teammates. In this paper, we formalize these differences and analyze metrics to characterize autonomous behavior in such human-robot cohabitation settings.

Lehnert's Plot Units (Lehnert 1981) or Rumelhart's Story Grammars (Rumelhart 1980), and naturally, one would like We give semiformal We aim at capturing the informal human notion of equivalence definitions in § 2 and then give a few examples (without any of stories in a formal system in such a way that formal details) in § 3. two stories are perceived as equivalent when their formal representations are isomorphic (cf. There is no unique "human Comparing the adequacy of frameworks is not a formal task, notion of equivalence of stories" as the research on analogical but deals with the degree of representation of the informal reasoning shows (Rattermann and Gentner 1987; notions in the formal setting.

Speedup learning seeks to improve the computational efficiency of problem solving with experience. In this paper, we develop a formal framework for learning efficient problem solving from random problems and their solutions. We apply this framework to two different representations of learned knowledge, namely control rules and macro-operators, and prove theorems that identify sufficient conditions for learning in each representation. Our proofs are constructive in that they are accompanied with learning algorithms. Our framework captures both empirical and explanation-based speedup learning in a unified fashion. We illustrate our framework with implementations in two domains: symbolic integration and Eight Puzzle. This work integrates many strands of experimental and theoretical work in machine learning, including empirical learning of control rules, macro-operator learning, Explanation-Based Learning (EBL), and Probably Approximately Correct (PAC) Learning.