Imagen de Portada

Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	McNichols, Hunter, Scarlatos, Alexander, Dascalu, Mihai, McNamara, Danielle, Lan, Andrew
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gumbel Counterfactual Generation From Language Models
por: Ravfogel, Shauli, et al.
Publicado: (2024)

The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course
por: McNichols, Hunter, et al.
Publicado: (2025)

Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
por: Lee, Jaewook, et al.
Publicado: (2024)

Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning
por: McNichols, Hunter, et al.
Publicado: (2023)

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
por: Lee, Jaewook, et al.
Publicado: (2025)

RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning
por: Scarlatos, Alexander, et al.
Publicado: (2023)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
por: Huang, Shuyan, et al.
Publicado: (2026)

Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models
por: Feng, Wanyong, et al.
Publicado: (2024)

Applying Natural Language Processing and Hierarchical Machine Learning Approaches to Text Difficulty Classification
por: Balyan, Renu, et al.
Publicado: (2020)

Applying Natural Language Processing and Hierarchical Machine Learning Approaches to Text Difficulty Classification
por: Balyan, Renu, et al.
Publicado: (2020)

Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models
por: Tian, Yu, et al.
Publicado: (2026)

Rethinking Vacuity for OOD Detection in Evidential Deep Learning
por: McNamara, Claire
Publicado: (2026)

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
por: Fu, Jiayi, et al.
Publicado: (2024)

Can Large Language Models Replicate ITS Feedback on Open-Ended Math Questions?
por: McNichols, Hunter, et al.
Publicado: (2024)

Value-Aware Numerical Representations for Transformer Language Models
por: Dutulescu, Andreea, et al.
Publicado: (2026)

Gumbel Distillation for Parallel Text Generation
por: Zhang, Chi, et al.
Publicado: (2026)

Waste Not, Want Not; Recycled Gumbel Noise Improves Consistency in Natural Language Generation
por: de Mijolla, Damien, et al.
Publicado: (2025)

Letting Tutor Personas "Speak Up" for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization
por: Lee, Jaewook, et al.
Publicado: (2026)

Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning
por: Ugadiarov, Leonid, et al.
Publicado: (2026)

Counterfactual Simulatability of LLM Explanations for Generation Tasks
por: Limpijankit, Marvin, et al.
Publicado: (2025)

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
por: Ikram, Fareya, et al.
Publicado: (2025)

Demystifying AI Agents: The Final Generation of Intelligence
por: McNamara, Kevin J, et al.
Publicado: (2025)

The Initial Exploration Problem in Knowledge Graph Exploration
por: McNamara, Claire, et al.
Publicado: (2026)

A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers
por: McAleese, Stephen, et al.
Publicado: (2024)

Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs
por: Scarlatos, Alexander, et al.
Publicado: (2024)

Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
por: Koo, Jabin, et al.
Publicado: (2026)

LookAlike: Consistent Distractor Generation in Math MCQs
por: Parikh, Nisarg, et al.
Publicado: (2025)

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
por: Zheng, Zhi, et al.
Publicado: (2025)

On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
por: Liu, Yule, et al.
Publicado: (2024)

Gumbel Reranking: Differentiable End-to-End Reranker Optimization
por: Huang, Siyuan, et al.
Publicado: (2025)

Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
por: Scarlatos, Alexander, et al.
Publicado: (2024)

Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
por: Hoffmann, Marcel, et al.
Publicado: (2025)

Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation
por: Soor, Sampriti, et al.
Publicado: (2025)

Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise
por: Hong, Giwon, et al.
Publicado: (2023)

Simulated Students in Tutoring Dialogues: Substance or Illusion?
por: Scarlatos, Alexander, et al.
Publicado: (2026)

Aprender del texto: Efectos de la estructura textual y las estrategias del lector
por: Danielle S McNamara
Publicado: (2004)

Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions
por: Nair, Inderjeet, et al.
Publicado: (2024)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
por: Lv, Hang, et al.
Publicado: (2025)

WritingBench: A Comprehensive Benchmark for Generative Writing
por: Wu, Yuning, et al.
Publicado: (2025)

Self-Steering Language Models
por: Grand, Gabriel, et al.
Publicado: (2025)