Imagen de Portada

LLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ai, Lun, Langer, Johannes, Schmid, Ute, Muggleton, Stephen
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Explanatory machine learning for sequential human teaching
por: Ai, Lun, et al.
Publicado: (2022)

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models
por: Ai, Lun, et al.
Publicado: (2024)

Active learning of digenic functions with boolean matrix logic programming
por: Ai, Lun, et al.
Publicado: (2024)

CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations
por: Motzkus, Franz, et al.
Publicado: (2024)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
por: Lee, Yu-Ang, et al.
Publicado: (2026)

Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions
por: Golowich, Noah, et al.
Publicado: (2024)

Reflective-Net: Learning from Explanations
por: Schneider, Johannes, et al.
Publicado: (2020)

The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding
por: Saribatur, Zeynep G., et al.
Publicado: (2026)

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR
por: Adewuyi, Israel, et al.
Publicado: (2026)

Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning
por: Straka, Matej, et al.
Publicado: (2025)

Robust Counterfactual Explanations in Machine Learning: A Survey
por: Jiang, Junqi, et al.
Publicado: (2024)

The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanations
por: Christodoulou, Leonidas, et al.
Publicado: (2026)

Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
por: Xiang, Yuanfang, et al.
Publicado: (2025)

Simulating Petri nets with Boolean Matrix Logic Programming
por: Ai, Lun, et al.
Publicado: (2024)

NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
por: Rose, Daniel, et al.
Publicado: (2025)

Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models
por: Löfström, Tuwe, et al.
Publicado: (2024)

rePIRL: Learn PRM with Inverse RL for LLM Reasoning
por: Wu, Xian, et al.
Publicado: (2026)

What Do Machine Learning Researchers Mean by "Reproducible"?
por: Raff, Edward, et al.
Publicado: (2024)

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
por: Zhang, Yuanhe, et al.
Publicado: (2025)

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
por: Mukherjee, Sagnik, et al.
Publicado: (2026)

Uncovering the Structure of Explanation Quality with Spectral Analysis
por: Maeß, Johannes, et al.
Publicado: (2025)

Example-based Explanations for Random Forests using Machine Unlearning
por: Surve, Tanmay, et al.
Publicado: (2024)

UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
por: Zou, Sunan, et al.
Publicado: (2025)

Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
por: Manchingal, Shireen Kudukkil
Publicado: (2025)

Bayesian Networks and Machine Learning for COVID-19 Severity Explanation and Demographic Symptom Classification
por: Ajayi, Oluwaseun T., et al.
Publicado: (2024)

Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
por: Prieto, Nicolás Villagrán, et al.
Publicado: (2026)

Generating Counterfactual Explanations Using Cardinality Constraints
por: Ruiz-Torrubiano, Rubén
Publicado: (2024)

Robust Stochastic Graph Generator for Counterfactual Explanations
por: Prado-Romero, Mario Alfonso, et al.
Publicado: (2023)

Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction
por: van Oerle, P., et al.
Publicado: (2025)

Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets
por: Bendinelli, Tommaso, et al.
Publicado: (2025)

Counterfactual Explanations for Continuous Action Reinforcement Learning
por: Dong, Shuyang, et al.
Publicado: (2025)

Global Concept Explanations for Graphs by Contrastive Learning
por: Teufel, Jonas, et al.
Publicado: (2024)

CohEx: A Generalized Framework for Cohort Explanation
por: Meng, Fanyu, et al.
Publicado: (2024)

Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning
por: Franceschelli, Giorgio, et al.
Publicado: (2024)

Flexible Counterfactual Explanations with Generative Models
por: Hellemans, Stig, et al.
Publicado: (2025)

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
por: Mayne, Harry, et al.
Publicado: (2026)

Selecting the Right LLM for eGov Explanations
por: Limonad, Lior, et al.
Publicado: (2025)

Not All Explanations for Deep Learning Phenomena Are Equally Valuable
por: Jeffares, Alan, et al.
Publicado: (2025)

Quantifying the Gain in Weak-to-Strong Generalization
por: Charikar, Moses, et al.
Publicado: (2024)

Learning Concept Bottleneck Models from Mechanistic Explanations
por: De Santis, Antonio, et al.
Publicado: (2026)