Learning to Complement and to Defer to Multiple Users

• URL: http://arxiv.org/abs/2407.07003v1
• Date: Tue, 9 Jul 2024 16:16:44 GMT
• Title: Learning to Complement and to Defer to Multiple Users
• Abstract summary: Human-AI Collaboration in Classification (HAI-CC) aims to integrate users and AI predictions. LECODU combines learning to complement and learning to defer strategies. It incorporates an estimation of the optimal number of users to engage in the decision process. Comprehensive evaluations demonstrate LECODU's superior performance compared to state-of-the-art HAI-CC methods.
• Score: 19.22186542262498
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users, and 3) learning to defer, where AI defers to users. Despite their interconnected nature, these options have been studied in isolation rather than as components of a unified system. In this paper, we address this weakness with the novel HAI-CC methodology, called Learning to Complement and to Defer to Multiple Users (LECODU). LECODU not only combines learning to complement and learning to defer strategies, but it also incorporates an estimation of the optimal number of users to engage in the decision process. The training of LECODU maximises classification accuracy and minimises collaboration costs associated with user involvement. Comprehensive evaluations across real-world and synthesized datasets demonstrate LECODU's superior performance compared to state-of-the-art HAI-CC methods. Remarkably, even when relying on unreliable users with high rates of label noise, LECODU exhibits significant improvement over both human decision-makers alone and AI alone.

Related papers

• Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing [66.03354630509942]
  This paper reports on a study where we compare three designs for user-AI interaction in a learning context.<n>Fifty study participants were tasked with learning about nuclear safety protocols.
  arXiv  Detail & Related papers  (2026-09-01T02:24:35Z)
• The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration [0.904861150954008]
  Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration.<n>Sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making.<n>This study investigates how sycophantic alignment emerges in authentic multi-turn human-AI interactions.
  arXiv  Detail & Related papers  (2026-05-18T13:20:45Z)
• L2CU: Learning to Complement Unseen Users [15.25018543473196]
  We introduce L2CU, a novel framework for human-AI cooperative classification with unseen users.<n>Given sparse and noisy user annotations, L2CU identifies representative annotator profiles capturing distinct labeling patterns.<n>By matching unseen users to these profiles, L2CU leverages profile-specific models to complement the user and achieve superior joint accuracy.
  arXiv  Detail & Related papers  (2026-01-03T20:30:48Z)
• UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models [59.693733170193944]
  Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings.<n>Recent reinforcement learning approaches address this limitation but face two critical challenges.<n>We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges.
  arXiv  Detail & Related papers  (2025-11-12T01:27:02Z)
• UserRL: Training Interactive User-Centric Agent via Reinforcement Learning [104.63494870852894]
  Reinforcement learning (RL) has shown promise in training agentic models that engage in dynamic, multi-turn interactions.<n>We propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments.
  arXiv  Detail & Related papers  (2025-09-24T03:33:20Z)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback [59.768119380109084]
  This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback.<n>We propose RiCL, a Reinforced interactive Continual Learning framework leveraging Large Language Models (LLMs)<n>Our RiCL approach substantially outperforms existing combinations of state-of-the-art online continual learning and noisy-label learning methods.
  arXiv  Detail & Related papers  (2025-05-15T03:22:03Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts. With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS) Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements. High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Coverage-Constrained Human-AI Cooperation with Multiple Experts [21.247853435529446]
  We propose the Coverage-constrained Learning to Defer and Complement with Specific Experts (CL2DC) method. CL2DC makes final decisions through either AI prediction alone or by deferring to or complementing a specific expert. It achieves superior performance compared to state-of-the-art HAI-CC methods.
  arXiv  Detail & Related papers  (2024-11-18T19:06:01Z)
• Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
  We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks. We show that the learned AI control system demonstrates robustness against adversarial tampering. In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
  arXiv  Detail & Related papers  (2024-07-03T15:38:57Z)
• How do machines learn? Evaluating the AIcon2abs method [0.0]
  This study is an expansion of a previous work aiming to evaluate the AIcon2abs method (AI from Concrete to Abstract: Demystifying Artificial Intelligence to the general public) The approach employs the WiSARD algorithm, a weightless neural network known for its simplicity, and user accessibility. WiSARD does not require Internet, making it ideal for non-technical users and resource-limited environments.
  arXiv  Detail & Related papers  (2024-01-14T22:40:58Z)
• Learning to Complement with Multiple Humans [21.247853435529446]
  This paper introduces the innovative Learning to Complement with Multiple Humans (LECOMH) approach. LECOMH is designed to learn from noisy labels without depending on clean labels, simultaneously maximising collaborative accuracy. New benchmarks featuring multiple noisy labels for both training and testing are proposed to evaluate HAI-CC methods.
  arXiv  Detail & Related papers  (2023-11-22T05:31:06Z)
• Improving Generalization of Alignment with Human Preferences through Group Invariant Learning [56.19242260613749]
  Reinforcement Learning from Human Feedback (RLHF) enables the generation of responses more aligned with human preferences. Previous work shows that Reinforcement Learning (RL) often exploits shortcuts to attain high rewards and overlooks challenging samples. We propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
  arXiv  Detail & Related papers  (2023-10-18T13:54:15Z)
• Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment [66.91538273487379]
  There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data.
  arXiv  Detail & Related papers  (2023-02-13T16:44:44Z)
• Learning Complementary Policies for Human-AI Teams [22.13683008398939]
  We propose a framework for a novel human-AI collaboration for selecting advantageous course of action. Our solution aims to exploit the human-AI complementarity to maximize decision rewards.
  arXiv  Detail & Related papers  (2023-02-06T17:22:18Z)
• Advancing Human-AI Complementarity: The Impact of User Expertise and Algorithmic Tuning on Joint Decision Making [10.890854857970488]
  Many factors can impact success of Human-AI teams, including a user's domain expertise, mental models of an AI system, trust in recommendations, and more. Our study examined user performance in a non-trivial blood vessel labeling task where participants indicated whether a given blood vessel was flowing or stalled. Our results show that while recommendations from an AI-Assistant can aid user decision making, factors such as users' baseline performance relative to the AI and complementary tuning of AI error types significantly impact overall team performance.
  arXiv  Detail & Related papers  (2022-08-16T21:39:58Z)
• Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment [52.07473934146584]
  We guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level.
  arXiv  Detail & Related papers  (2022-08-04T23:53:51Z)
• Data-driven Koopman Operators for Model-based Shared Control of Human-Machine Systems [66.65503164312705]
  We present a data-driven shared control algorithm that can be used to improve a human operator's control of complex machines. Both the dynamics and information about the user's interaction are learned from observation through the use of a Koopman operator. We find that model-based shared control significantly improves task and control metrics when compared to a natural learning, or user only, control paradigm.
  arXiv  Detail & Related papers  (2020-06-12T14:14:07Z)
• Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork [54.309495231017344]
  We argue that AI systems should be trained in a human-centered manner, directly optimized for team performance. We study this proposal for a specific type of human-AI teaming, where the human overseer chooses to either accept the AI recommendation or solve the task themselves. Our experiments with linear and non-linear models on real-world, high-stakes datasets show that the most accuracy AI may not lead to highest team performance.
  arXiv  Detail & Related papers  (2020-04-27T19:06:28Z)
• Human AI interaction loop training: New approach for interactive reinforcement learning [0.0]
  Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. RL presents unique challenges with large amounts of environment states and action spaces, as well as in the determination of rewards. Imitation Learning (IL) offers a promising solution for those challenges using a teacher.
  arXiv  Detail & Related papers  (2020-03-09T15:27:48Z)

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.