arXiv subjects

Shanyong Wang

Publications and source records attributed to Shanyong Wang.

4 recordsLinked to original sources

arXiv2026

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving individual preferences. We present a new dataset, Value Conflict Dilemma (VCD), which includes scenarios that involve conflicting human preferences, facilitating the evaluation of our approach. Our experiments demonstrate that PFT outperforms single-preference training methods, achieving up to 96.6% accuracy in multi-choice classification tasks and the highest open-ended generation score of 8.69. PFT also shows significant improvements over DPO, SFT and some traditional training methods, especially when handling conflicting preferences. Additionally, with limited user history data, models can inferring preference vector rapidly, achieving a 44.76% improvement in user-specific preference alignment in comparison to single-preference models.

cs.CL↗

arXiv2025

A User-customized and Untethered Electro-haptic Device for Immersive Human-Machine Interaction

Haptic feedback is essential for human-machine interaction, as it bridges physical and digital experiences and enables immersive engagement with virtual environments. However, current haptic devices are frequently tethered, lack portability and flexibility. They also have limited ability to deliver fine-grained, multi-dimensional feedback. To address these challenges, we present a flexible, ultra-thin, and user-customized electro-haptic device fabricated with soft materials and printable liquid metal ink. Its highly integrated and lightweight design minimizes interference with natural hand movements while maintaining reliable skin contact. By delivering finely controlled electrical stimulation through 15 electrodes, it can evoke a wide range of tactile sensations that cover diverse interaction scenarios. Our user study demonstrates that the device is comfortable to wear and capable of generating tunable, precise electro-haptic feedback, thereby significantly enhancing immersion and realism in human-machine interactions.

cs.HC↗

arXiv2025

DecisionFlow: Advancing Large Language Model as Principled Decision Maker

In high-stakes domains such as healthcare and finance, effective decision-making demands not just accurate outcomes but transparent and explainable reasoning. However, current language models often lack the structured deliberation needed for such tasks, instead generating decisions and justifications in a disconnected, post-hoc manner. To address this, we propose DecisionFlow, a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints. Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function to evaluate trade-offs in a transparent, utility-driven manner. This process produces decisions tightly coupled with interpretable rationales reflecting the model's reasoning. Empirical results on two high-stakes benchmarks show that DecisionFlow not only achieves up to 30% accuracy gains over strong prompting baselines but also enhances alignment in outcomes. Our work is a critical step toward integrating symbolic reasoning with LLMs, enabling more accountable, explainable, and reliable LLM decision support systems. Code and data are at https://github.com/xiusic/DecisionFlow.

cs.CL↗

arXiv2023

Nonparametric approaches for analyzing carbon emission: from statistical and machine learning perspectives

Linear regression models, especially the extended STIRPAT model, are routinely-applied for analyzing carbon emissions data. However, since the relationship between carbon emissions and the influencing factors is complex, fitting a simple parametric model may not be an ideal solution. This paper investigated various nonparametric approaches in statistics and machine learning (ML) for modeling carbon emissions data, including kernel regression, random forest and neural network. We selected data from ten Chinese cities from 2005 to 2019 for modeling studies. We found that neural network had the best performance in both fitting and prediction accuracy, which implies its capability of expressing the complex relationships between carbon emissions and the influencing factors. This study provides a new means for quantitative modeling of carbon emissions research that helps to understand how to characterize urban carbon emissions and to propose policy recommendations for "carbon reduction". In addition, we used the carbon emissions data of Wuhu city as an example to illustrate how to use this new approach.

stat.AP↗