Related papers: Offloading Score: Measuring AI Reliance Through Co…
To improve reliability and the understanding of AI systems, there is increasing interest in the use of formal methods, e.g. model checking. Model checking tools produce a counterexample when a model does not satisfy a property.…
We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system's data inputs that causally drives the decision (i.e.,…
Several assistive technologies for users' operations have been recently developed. A user's sense of agency (SoA) decreases with increasing system assistance, possibly resulting in a decrease in the user's sense of fulfillment. This study…
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…
Generative AI tools are increasingly embedded in everyday work and learning, yet their fluency, opacity, and propensity to hallucinate mean that users must critically evaluate AI outputs rather than accept them at face value. The present…
Lean processes focus on doing only necessery things in an efficient way. Artificial intelligence and Machine Learning offer new opportunities to optimizing processes. The presented approach demonstrates an improvement of the test process by…
Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
Semi-structured interviews are a common method in qualitative research. However, conducting high-quality interviews is cognitively demanding and requires strong interviewing skills. To lower this bar, we propose InterFlow, an AI-powered…
Artificial intelligence (AI) systems have become increasingly popular in many areas. Nevertheless, AI technologies are still in their developing stages, and many issues need to be addressed. Among those, the reliability of AI systems needs…
This paper is about the possible negative impact of excessive collaboration on the performance of top employees. With the rise of participatory culture and developments in communications technology, management practices require greater…
Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 [Ho et al., 2024]. Running small-scale ablation experiments on key innovations from this time period, we are able to account…
Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…
Although popularized AI fairness metrics, e.g., demographic parity, have uncovered bias in AI-assisted decision-making outcomes, they do not consider how much effort one has spent to get to where one is today in the input feature space.…
Background: The increasing adoption of AI assistants in programming has led to numerous studies exploring their benefits. While developers consistently report significant productivity gains from these tools, empirical measurements often…
Proof autoformalization, the task of translating natural language theorems and proofs into machine-verifiable code, is a critical step for integrating large language models into rigorous mathematical workflows. Current approaches focus on…
To improve customer experience, datacenter operators offer support for simplifying application and resource management. For example, running workloads of workflows on behalf of customers is desirable, but requires increasingly more…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Language model agents are increasingly used to automate scientific research, yet evaluating their scientific contributions remains a challenge. A key mechanism to obtain such insights is through ablation experiments. To this end, we…
Understanding how AI systems are used by people in real situations that mirror aspects of both legitimate and illegitimate use is key to predicting the risks and benefits of AI systems. This is especially true in biological applications,…