Image de couverture de livre

Assessing model error in counterfactual worlds

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Howerton, Emily, Lessler, Justin
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Leveraging counterfactual concepts for debugging and improving CNN model performance
par: Tariq, Syed Ali, et autres
Publié: (2025)

Towards plausibility in time series counterfactual explanations
par: Kostrzewa, Marcin, et autres
Publié: (2026)

Evidence from counterfactual tasks supports emergent analogical reasoning in large language models
par: Webb, Taylor, et autres
Publié: (2024)

On Predictive planning and counterfactual learning in active inference
par: Paul, Aswin, et autres
Publié: (2024)

Robust image representations with counterfactual contrastive learning
par: Roschewitz, Mélanie, et autres
Publié: (2024)

Mitigating attribute amplification in counterfactual image generation
par: Xia, Tian, et autres
Publié: (2024)

Generative diffusion models for spatiotemporal influenza forecasting
par: Lemaitre, Joseph, et autres
Publié: (2026)

Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
par: Bobek, Szymon, et autres
Publié: (2025)

HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
par: Marszałek, Patryk, et autres
Publié: (2025)

When is using AI the rational choice? The importance of counterfactuals in AI deployment decisions
par: Lehner, Paul, et autres
Publié: (2025)

xai-cola: A Python library for sparsifying counterfactual explanations
par: Zhu, Lin, et autres
Publié: (2026)

RLInspect: An Interactive Visual Approach to Assess Reinforcement Learning Algorithm
par: Kalra, Geetansh, et autres
Publié: (2024)

Guiding the generation of counterfactual explanations through temporal background knowledge for Predictive Process Monitoring
par: Buliga, Andrei, et autres
Publié: (2024)

A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
par: Stępka, Ignacy, et autres
Publié: (2024)

Local Universal Explainer (LUX) -- a rule-based explainer with factual, counterfactual and visual explanations
par: Bobek, Szymon, et autres
Publié: (2023)

Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
par: Fujii, Keisuke, et autres
Publié: (2022)

Synthesizing world models for bilevel planning
par: Ahmed, Zergham, et autres
Publié: (2025)

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning
par: Robertson, Cole, et autres
Publié: (2025)

RO-Bench: Large-scale robustness evaluation of MLLMs with text-driven counterfactual videos
par: Yang, Zixi, et autres
Publié: (2025)

From monoliths to modules: Decomposing transducers for efficient world modelling
par: Boyd, Alexander, et autres
Publié: (2025)

Information-theoretic analysis of world models in optimal reward maximizers
par: Harwood, Alfred, et autres
Publié: (2026)

IWISDM: Assessing instruction following in multimodal models at scale
par: Lei, Xiaoxuan, et autres
Publié: (2024)

Building spatial world models from sparse transitional episodic memories
par: He, Zizhan, et autres
Publié: (2025)

Robust agents learn causal world models
par: Richens, Jonathan, et autres
Publié: (2024)

General agents contain world models
par: Richens, Jonathan, et autres
Publié: (2025)

Recovering implicit physics model under real-world constraints
par: Banerjee, Ayan, et autres
Publié: (2024)

Value-guided action planning with JEPA world models
par: Destrade, Matthieu, et autres
Publié: (2025)

Assessing win strength in MLB win prediction models
par: Allen, Morgan, et autres
Publié: (2025)

From task structures to world models: What do LLMs know?
par: Yildirim, Ilker, et autres
Publié: (2023)

Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays
par: Maksudov, Bulat, et autres
Publié: (2025)

Algebras of actions in an agent's representations of the world
par: Dean, Alexander, et autres
Publié: (2023)

ACSE-Eval: Can LLMs threat model real-world cloud infrastructure?
par: Munshi, Sarthak, et autres
Publié: (2025)

SOCK: A Benchmark for Measuring Self-Replication in Large Language Models
par: Chavarria, Justin, et autres
Publié: (2025)

Influence of the Geometry of the world model on Curiosity Based Exploration
par: Sergeant-Perthuis, Grégoire, et autres
Publié: (2023)

Transformers self-organize like newborn visual systems when trained in prenatal worlds
par: Pandey, Lalit, et autres
Publié: (2026)

Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
par: Zhang, Han, et autres
Publié: (2026)

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
par: Levy, Guillaume, et autres
Publié: (2025)

AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability
par: Rosas, Fernando, et autres
Publié: (2025)

Misapplied management makes matters worse: Spatially explicit control leverages biotic interactions to slow invasion
par: Emily Howerton, et autres
Publié: (2024)

Structured interactions improve distributed coordination beyond model scaling in a real-world multi-robot system
par: Wang, Junping, et autres
Publié: (2026)