Developing value-aligned agents is a complex undertaking and an ongoing challenge in the field of AI. Indeed, designing Large Language Models (LLMs) that can balance multiple possibly conflicting moral values based on the context is a problem of paramount importance. In this paper, we propose a system that performs contextual value alignment based on contextual aggregation of possible responses. This aggregation is achieved by integrating a subset of possible LLM responses that are best suited to a user's input while taking into account features extracted about the user's moral preferences. The proposed system trained using the Moral Integrity Corpus displays better alignment to human values than state-of-the-art baselines.

Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy, Elizabeth M. Daly, Kush R. Varshney, Eitan Farchi, Pierre Dognin, Jesus Rios, Djallel Bouneffouf, Miao Liu, Prasanna Sattigeri. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

We apply the machinery of interventional causal learning with programmable interventions to the domain of applications management. Modern applications are modularized into interdependent components or services (e.g. microservices) for ease of development and management. The communication graph among such components is a function of application code and is not always known to the platform provider. In our solution we learn this unknown communication graph solely using application logs observed during the execution of the application by using fault injections in a staging environment. Specifically, we have developed an active (or interventional) causal learning algorithm that uses the observations obtained during fault injections to learn a model of error propagation in the communication among the components. The “power of intervention” additionally allows us to address the presence of confounders in unobserved user interactions. We demonstrate the effectiveness of our solution in learning the communication graph of well-known microservice application benchmarks. We also show the efficacy of the solution on a downstream task of fault localization in which the learned graph indeed helps to localize faults at runtime in a production environment (in which the location of the fault is unknown). Additionally, we briefly discuss the implementation and deployment status of a fault injection framework which incorporates the developed technology.

Finding the exact location of a fault in a large distributed microservices application running in containerized cloud environments can be very difficult and time-consuming. We present a novel approach that uses distributed tracing to automatically detect, localize and aid in explaining application-level faults. We demonstrate the effectiveness of our proposed approach by injecting faults into a well-known microservice-based benchmark application. Our experiments demonstrated that the proposed fault localization algorithm correctly detects and localize the microservice with the injected fault. We also compare our approach with other fault localization methods. In particular, we empirically show that our method outperforms methods in which a graph model of error propagation is used for inferring fault locations using error logs. Our work illustrates the value added by distributed tracing for localizing and explaining faults in microservices.

Optimization of real-world black-box functions defined over purely categorical variables is an active area of research. In particular, optimization and design of biological sequences with specific functional or structural properties have a profound impact in medicine, materials science, and biotechnology. Standalone search algorithms, such as simulated annealing (SA) and Monte Carlo tree search (MCTS), are typically used for such optimization problems. In order to improve the performance and sample efficiency of such algorithms, we propose to use existing methods in conjunction with a surrogate model for the black-box evaluations over purely categorical variables. To this end, we present two different representations, a group-theoretic Fourier expansion and an abridged one-hot encoded Boolean Fourier expansion. To learn such representations, we consider two different settings to update our surrogate model. First, we utilize an adversarial online regression setting where Fourier characters of each representation are considered as experts and their respective coefficients are updated via an exponential weight update rule each time the black box is evaluated. Second, we consider a Bayesian setting where queries are selected via Thompson sampling and the posterior is updated via a sparse Bayesian regression model (over our proposed representation) with a regularized horseshoe prior. Numerical experiments over synthetic benchmarks as well as real-world RNA sequence optimization and design problems demonstrate the representational power of the proposed methods, which achieve competitive or superior performance compared to state-of-the-art counterparts, while improving the computation cost and/or sample efficiency, substantially.

In today’s IT environment with a growing number of costly outages, increasing complexity of the systems, and availability of massive operational data, there is a strengthening demand to effectively leverage Artificial Intelligence and Machine Learning (AI/ML) towards enhanced resiliency. In this paper, we present an automatic fault injection platform to enable and optimize the generation of data needed for building AI/ML models to support modern IT operations. The merits of our platform include the ease of use, the possibility to orchestrate complex fault scenarios and to optimize the data generation for the modeling task at hand. Specifically, we designed a fault injection service that (i) combines fault injection with data collection in a unified framework, (ii) supports hybrid and multi-cloud environments, and (iii) does not require programming skills for its use. Our current implementation covers the most common fault types both at the application and infrastructure levels. The platform also includes some AI capabilities. In particular, we demonstrate the interventional causal learning capability currently available in our platform. We show how our system is able to learn a model of error propagation in a micro-service application in a cloud environment (when the communication graph among micro-services is unknown and only logs are available) for use in subsequent applications such as fault localization.

We consider the problem of black-box function optimization over the Boolean hypercube. Despite the vast literature on black-box function optimization over continuous domains, not much attention has been paid to learning models for optimization over combinatorial domains until recently. However, the computational complexity of the recently devised algorithms are prohibitive even for moderate numbers of variables; drawing one sample using the existing algorithms is more expensive than a function evaluation for many black-box functions of interest. To address this problem, we propose a computationally efficient model learning algorithm based on multilinear polynomials and exponential weight updates. In the proposed algorithm, we alternate between simulated annealing with respect to the current polynomial representation and updating the weights using monomial experts' advice. Numerical experiments on various datasets in both unconstrained and sum-constrained Boolean optimization indicate the competitive performance of the proposed algorithm, while improving the computational time up to several orders of magnitude compared to state-of-the-art algorithms in the literature.

Economic systems are rife with heterogeneous risk events that have the potential to cause disruption. The diversity of risk types makes it challenging for companies to conduct comprehensive risk analysis for any chosen business opportunity. The current practice is laborious and expensive, involving internal risk analysts and external risk advisory services. In this paper, we present a cognitive system that augments human abilities, with the objective of drastic improvements in the productivity of risk analysis efforts. Our system is provided with a comprehensive risk taxonomy and its textual description along with an extensive corpus of textual data such as news articles. Using a series of textual analysis, knowledge extraction and machine learning techniques, the data corpus is annotated with risk-related information and indexed in a risk store for flexible query and retrieval. Our system interfaces with the risk analyst using a query orchestrator which translates analyst queries that are posed at a high level into lower level queries that are expanded to exploit the system's risk-related knowledge. It also enables formulating a graphical model and assessing the required probabilities; we introduce a particular family of models that can succinctly represent risk events modeled as stochastic processes over a long time horizon. We illustrate how a risk analyst can query the system to build a risk model with the help of a case study.