ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

• URL: http://arxiv.org/abs/2503.04569v1
• Date: Thu, 06 Mar 2025 16:02:53 GMT
• Title: ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making
• Abstract summary: We propose a two-phase value-driven decision-making framework comprising a dataset generation toolkit DGT and a decision-making module DMM trained on the generated data.<n>DGT is capable of generating scenarios based on value dimensions and closely mirroring real-world tasks, with automated filtering techniques and human curation to ensure the validity of the dataset.<n>In the generated dataset, DMM learns to recognize the inherent values of scenarios, computes action feasibility and navigates the trade-offs between multiple value dimensions to make personalized decisions.
• Score: 4.392948275297139
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent advances in artificial intelligence (AI), it poses challenges to ensure personalized decision-making in tasks that are not considered in training datasets. To address this issue, we propose ValuePilot, a two-phase value-driven decision-making framework comprising a dataset generation toolkit DGT and a decision-making module DMM trained on the generated data. DGT is capable of generating scenarios based on value dimensions and closely mirroring real-world tasks, with automated filtering techniques and human curation to ensure the validity of the dataset. In the generated dataset, DMM learns to recognize the inherent values of scenarios, computes action feasibility and navigates the trade-offs between multiple value dimensions to make personalized decisions. Extensive experiments demonstrate that, given human value preferences, our DMM most closely aligns with human decisions, outperforming Claude-3.5-Sonnet, Gemini-2-flash, Llama-3.1-405b and GPT-4o. This research is a preliminary exploration of value-driven decision-making. We hope it will stimulate interest in value-driven decision-making and personalized decision-making within the community.

Related papers

• Reinforcement Learning Measurement Model [12.072526858407505]
  We propose the Reinforcement Learning Measurement Model (RLMM), a measurement framework that decouples person-level choice sensitivity from task-level value representation.<n>The model combines a Boltzmann choice rule with normalized advantages, a soft Bellman penalty, and a block-coordinate MAP procedure for joint estimation.
  arXiv  Detail & Related papers  (2026-05-10T04:02:35Z)
• DecisionLLM: Large Language Models for Long Sequence Decision Exploration [26.033533195580933]
  Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning and planning tasks.<n>This work investigates the application of LLMs to offline decision making tasks.<n>By learning to align trajectory data with natural language task descriptions, our model can autoregressively predict future decisions.
  arXiv  Detail & Related papers  (2026-01-15T07:42:02Z)
• ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making [11.176700333939278]
  We propose a value-driven approach to personalized decision-making.<n>Human values serve as stable, transferable signals that support consistent and generalizable behavior.<n>We introduce ValuePilot, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM)
  arXiv  Detail & Related papers  (2025-12-09T12:15:46Z)
• Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG [51.120170062795566]
  We propose Divide-Then-Align (DTA) to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary.<n>DTA balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.
  arXiv  Detail & Related papers  (2025-05-27T08:21:21Z)
• Beyond the Generative Learning Trilemma: Generative Model Assessment in Data Scarcity Domains [1.2769300783938085]
  Deep Generative Models (DGMs) produce synthetic data that satisfies the Generative Learning Trilemma: fidelity, diversity, and sampling efficiency. We extend the trilemma to include utility, robustness, and privacy, factors crucial for ensuring the applicability of DGMs in real-world scenarios. This study broadens the scope of the Generative Learning Trilemma, aligning it with real-world demands and providing actionable guidance for selecting DGMs tailored to specific applications.
  arXiv  Detail & Related papers  (2025-04-14T13:15:44Z)
• D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning [29.019199700339083]
  Small, high-quality datasets can equip large language models with instruction-following capabilities. We propose the D3 method comprising two key steps of scoring and selection. Experiments on three datasets demonstrate the effectiveness of D3 in endowing LLMs with competitive or even superior instruction-following capabilities.
  arXiv  Detail & Related papers  (2025-03-14T14:28:19Z)
• MetaTrading: An Immersion-Aware Model Trading Framework for Vehicular Metaverse Services [94.61039892220037]
  We propose an immersion-aware model trading framework that facilitates data provision for services while ensuring privacy through federated learning (FL) We design an incentive mechanism to incentivize metaverse users (MUs) to contribute high-value models under resource constraints. We develop a fully distributed dynamic reward algorithm based on deep reinforcement learning, without accessing any private information about MUs and other MSPs.
  arXiv  Detail & Related papers  (2024-10-25T16:20:46Z)
• Towards Cost Sensitive Decision Making [14.279123976398926]
  In this work, we consider RL models that may actively acquire features from the environment to improve the decision quality and certainty. We propose the Active-Acquisition POMDP and identify two types of the acquisition process for different application domains. In order to assist the agent in the actively-acquired partially-observed environment and alleviate the exploration-exploitation dilemma, we develop a model-based approach.
  arXiv  Detail & Related papers  (2024-10-04T19:48:23Z)
• Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark [69.02666229531322]
  We introduce a pioneering study that investigates Modality-Incomplete Industrial Anomaly Detection (MIIAD)<n>We find that most existing MIAD methods perform poorly on the MIIAD Bench, leading to significant performance degradation.<n>We propose a novel two-stage Robust modAlity-aware fusing and Detecting framewoRk, abbreviated as RADAR.
  arXiv  Detail & Related papers  (2024-10-02T16:47:55Z)
• Making Large Language Models Better Planners with Reasoning-Decision Alignment [70.5381163219608]
  We motivate an end-to-end decision-making model based on multimodality-augmented LLM. We propose a reasoning-decision alignment constraint between the paired CoTs and planning results. We dub our proposed large language planners with reasoning-decision alignment as RDA-Driver.
  arXiv  Detail & Related papers  (2024-08-25T16:43:47Z)
• Open-Source Drift Detection Tools in Action: Insights from Two Use Cases [0.0]
  D3Bench examines the capabilities of Evidently AI, NannyML, and Alibi-Detect, leveraging real-world data from two smart building use cases. We consider a comprehensive set of non-functional criteria, such as the integrability with ML pipelines, the adaptability to diverse data types, user-friendliness, computational efficiency, and resource demands. Our findings reveal that Evidently AI stands out for its general data drift detection, whereas NannyML excels at pinpointing the precise timing of shifts and evaluating their consequent effects on predictive accuracy.
  arXiv  Detail & Related papers  (2024-04-29T13:13:10Z)
• D2E-An Autonomous Decision-making Dataset involving Driver States and Human Evaluation [6.890077875318333]
  Driver to Evaluation dataset (D2E) is an autonomous decision-making dataset. It contains data on driver states, vehicle states, environmental situations, and evaluation scores from human reviewers. D2E contains over 1100 segments of interactive driving case data covering from human driver factor to evaluation results.
  arXiv  Detail & Related papers  (2024-04-12T21:29:18Z)
• Data-Driven Offline Decision-Making via Invariant Representation Learning [97.49309949598505]
  offline data-driven decision-making involves synthesizing optimized decisions with no active interaction. A key challenge is distributional shift: when we optimize with respect to the input into a model trained from offline data, it is easy to produce an out-of-distribution (OOD) input that appears erroneously good. In this paper, we formulate offline data-driven decision-making as domain adaptation, where the goal is to make accurate predictions for the value of optimized decisions.
  arXiv  Detail & Related papers  (2022-11-21T11:01:37Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• R(Det)^2: Randomized Decision Routing for Object Detection [64.48369663018376]
  We propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection. To facilitate effective learning, we propose randomized decision routing with node selective and associative losses. We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)$2$.
  arXiv  Detail & Related papers  (2022-04-02T07:54:58Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)

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.