Model Multiplicity
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices
arXiv:2606.07857v1 Announce Type: new Abstract: The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preservation and real-time responsiveness. However, distributed fine-tuning of language models on untrusted or heterogeneous edge nodes introduces new vulnerabilities.
Model Multiplicity and Predictive Arbitrariness in Recidivism Risk Assessment
arXiv:2606.02198v1 Announce Type: new Abstract: Prediction tasks over individual futures, which are inherently noisy, often admit multiple similarly accurate models. When these models produce different predictions for the same individual, they raise concerns of arbitrariness in decision-making. How severe can this arbitrariness be, in theory and in practice?
Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
Announce Type: new Abstract: Counterfactual explanations (CEs) are essential for actionable recourse, yet their reliability is often compromised in low-density regions, where classifiers exhibit high variance. Unlike existing methods that rely on expensive ensemble intersections to define stability, we propose \textit{DensityFlow}, a generative framework that constructs robust CEs by adhering to the high-confidence data manifold. Specifically, we model the counterfactual generation as...
One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems
arXiv:2606.09293v1 Announce Type: new Abstract: Dialogue systems in e-commerce scenarios often need to satisfy multiple objectives: accurately reasoning over user profiles (e.g., eligibility, credit limit) to ensure correct decision-making and user state interpretation, while also generating natural and faithful responses. These goals are complementary but not identical. In this work, we propose MORE, an adaptive Multi-Objective REinforcement learning framework that jointly optimizes...
Semantic Forwarding and Codebook-Enhanced Model Division Multiple Access for Satellite-Terrestrial Networks
arXiv:2603.02536v2 Announce Type: replace Abstract: Satellite-terrestrial communications are severely constrained by high path loss, limited spectrum resources, and time-varying channel conditions, rendering conventional bit-level transmission schemes inefficient and fragile, particularly in low signal-to-noise ratio (SNR) regimes. Semantic communication has emerged as a promising paradigm to address these challenges by prioritizing task-relevant information over exact bit recovery. In this...
Structure-Aware Modeling of Multiple-Choice Questions Improves Automatic Difficulty Estimation
arXiv:2606.08988v1 Announce Type: new Abstract: Automatic Question Difficulty Estimation (AQDE) holds growing promise for educational assessment because it has the potential to yield difficulty estimates that are competitive with expert judgment, while helping reduce the time and financial burden associated with pilot administrations and scaling to digital testing contexts. Prior AQDE studies report mixed evidence on whether adding distractors as additional text to the question stem and the...
When Do Diffusion Models learn to Generate Multiple Objects?
arXiv:2605.00273v2 Announce Type: replace Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself.
Modelling habitat suitability for multiple priority weed species to predict invasion hotspots for strategic management in complex landscapes
Established invasive alien plant species require ongoing, costly management to reduce harm to agricultural and environmental values. Heterogeneous landscapes are often under threat from multiple long-established invasive plants, whose simultaneous management presents strategic and tactical challenges. Systematic monitoring of weed populations enables more strategic management by providing more detailed insights into invasion threats than the more readily available presence-only data.
Structure-Informed Multiple Sequence Alignment: A Formal Model and Hardness Results
Announce Type: new Abstract: We formulate a structure-informed multiple sequence alignment problem, denoted MSA-S. The model abstracts biological sequences as strings and structural information as designated position-pairs. It augments a fixed pairwise string score, defined by a fixed non-gap symbol-pair scoring rule and fixed affine gap penalties, with a binary overlap score on designated position-pairs, which can be interpreted as a contact-map overlap score in structural applications....
Learning to model pediatric asthma exacerbation from multiple risk factors: a case study in coastal Virginia
Announce Type: new Abstract: Childhood asthma is a common illness exacerbated by air pollution as well as meteorological and neighborhood-level socioeconomic factors. Modeling asthma exacerbation (AE) in large spatiotemporal datasets requires disentangling impacts from multiple contributors. In this case study, we compared three techniques that balance predictive power with interpretability to predict AE in Hampton Roads, a coastal Virginia region comprising 7 cities and over 1.5 million people.