Algorithmic Feature Highlighting for Human-AI Decision-Making

• URL: http://arxiv.org/abs/2604.22236v1
• Date: Fri, 24 Apr 2026 05:23:06 GMT
• Title: Algorithmic Feature Highlighting for Human-AI Decision-Making
• Abstract summary: We study algorithms that highlight a small subset of case-specific features for human consideration.<n>A central issue is how humans interpret the algorithm's choice of features.<n>We show that optimizing highlighting for sophisticated agents can be computationally intractable.
• Score: 2.7830690575074435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate all available information. In such settings, we study algorithms that highlight a small subset of case-specific features for human consideration, rather than producing a single prediction or recommendation. We model highlighting as a constrained information policy that selects a small number of features to reveal. A central issue is how humans interpret the algorithm's choice of features: a sophisticated agent correctly conditions on the selection rule, while a naive agent updates only on revealed feature values and treats the selection event as exogenous. We show that optimizing highlighting for sophisticated agents can be computationally intractable, even in simple discrete and binary settings, whereas optimizing for naive agents is tractable as long as the maximal bandwidth is fixed. We also show that a highlighting policy that is optimal for sophisticated agents can perform arbitrarily poorly when deployed to naive agents, motivating robust, implementable alternatives. We illustrate our framework in a calibrated empirical exercise based on the American Housing Survey. Overall, our results establish the value of highlighting a context-specific set of features rather than a fixed one as a practically appealing and computationally feasible tool for achieving human-algorithm complementarity.

Related papers

• AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds [58.529749203758634]
  Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments.<n>We introduce AlgoWorlds, a benchmark that transforms formally specified optimization problems into partially observed decision environments.<n>AlgoWorlds contains 240 environments covering ten optimization families and four workload levels.
  arXiv  Detail & Related papers  (2026-08-29T18:37:41Z)
• An Empirical Study of Feature Selection Granularity [3.3545793786322347]
  Conventional feature selection algorithms compute feature importance scores globally across the entire feature set and then select the top-ranked features in a single step.<n>This approach raises a critical question: Can the presence of less informative (or noisy) features mask or obscure the true importance of other, more relevant features?
  arXiv  Detail & Related papers  (2026-07-27T08:24:40Z)
• Strategic Feature Selection [62.74494413516484]
  We study strategic classification through feature selection and its interaction with ridge regularization.<n>We provide a fine-grained characterization of the performance of a feature subset under optimal regularization.<n>Motivated by this characterization, we develop a practical algorithm for jointly choosing the feature set and the level of ridge regularization.
  arXiv  Detail & Related papers  (2026-06-17T09:47:15Z)
• Outsourced Privacy-Preserving Feature Selection Based on Fully Homomorphic Encryption [0.0]
  Feature selection is a technique that extracts a meaningful subset from a set of features in training data.<n>This study proposes a privacy-preserving model for feature selection.
  arXiv  Detail & Related papers  (2025-05-19T08:55:56Z)
• Satisficing Exploration for Deep Reinforcement Learning [26.73584163318647]
  In complex environments that approach the vastness and scale of the real world, attaining optimal performance may in fact be an entirely intractable endeavor. Recent work has leveraged tools from information theory to design agents that deliberately forgo optimal solutions in favor of sufficiently-satisfying or satisficing solutions. We extend an agent that directly represents uncertainty over the optimal value function allowing it to both bypass the need for model-based planning and to learn satisficing policies.
  arXiv  Detail & Related papers  (2024-07-16T21:28:03Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• Experience in Engineering Complex Systems: Active Preference Learning with Multiple Outcomes and Certainty Levels [1.5257326975704795]
  Black-box optimization refers to the problem whose objective function and/or constraint sets are either unknown, inaccessible, or non-existent. The algorithm so-called Active Preference Learning has been developed to exploit this specific information. Our approach aims to extend the algorithm in such a way that can exploit further information effectively.
  arXiv  Detail & Related papers  (2023-02-27T15:55:37Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Byzantine-Robust Online and Offline Distributed Reinforcement Learning [60.970950468309056]
  We consider a distributed reinforcement learning setting where multiple agents explore the environment and communicate their experiences through a central server. $alpha$-fraction of agents are adversarial and can report arbitrary fake information. We seek to identify a near-optimal policy for the underlying Markov decision process in the presence of these adversarial agents.
  arXiv  Detail & Related papers  (2022-06-01T00:44:53Z)
• Compactness Score: A Fast Filter Method for Unsupervised Feature Selection [66.84571085643928]
  We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features. Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
  arXiv  Detail & Related papers  (2022-01-31T13:01:37Z)
• Unpacking the Black Box: Regulating Algorithmic Decisions [1.283555556182245]
  We propose a model of oversight over 'black-box' algorithms used in high-stakes applications such as lending, medical testing, or hiring. We show that allowing for complex algorithms can improve welfare, but the gains depend on how the regulator regulates them.
  arXiv  Detail & Related papers  (2021-10-05T23:20:25Z)
• Adversarial Option-Aware Hierarchical Imitation Learning [89.92994158193237]
  We propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-10T06:42:05Z)
• Fairness-Aware Unsupervised Feature Selection [37.13136799987164]
  We develop a principled framework for a fairness-aware unsupervised feature selection problem. Our proposed framework can be regarded as a model-agnostic debiasing strategy. Experimental results on multiple real-world datasets demonstrate that our framework achieves a good trade-off between utility and fairness promotion.
  arXiv  Detail & Related papers  (2021-06-04T02:38:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.