Imagen de Portada

Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Voigt, Henrik, Habeck, Michael, Giesen, Joachim
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning 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

Analyzing Generalization in Pre-Trained Symbolic Regression
por: Voigt, Henrik, et al.
Publicado: (2025)

Scaling Up Unbiased Search-based Symbolic Regression
por: Kahlmeyer, Paul, et al.
Publicado: (2025)

Neural Task Synthesis for Visual Programming
por: Pădurean, Victor-Alexandru, et al.
Publicado: (2023)

In-context Pretraining: Language Modeling Beyond Document Boundaries
por: Shi, Weijia, et al.
Publicado: (2023)

Generating Pragmatic Examples to Train Neural Program Synthesizers
por: Vaduguru, Saujas, et al.
Publicado: (2023)

Emergent Representations of Program Semantics in Language Models Trained on Programs
por: Jin, Charles, et al.
Publicado: (2023)

Adaptive-Boundary-Clipping GRPO: Ensuring Bounded Ratios for Stable and Generalizable Training
por: Liu, Chi, et al.
Publicado: (2026)

Mapping Post-Training Forgetting in Language Models at Scale
por: Harmon, Jackson, et al.
Publicado: (2025)

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
por: Damani, Mehul, et al.
Publicado: (2025)

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
por: Puri, Isha, et al.
Publicado: (2026)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
por: Shivagunde, Namrata, et al.
Publicado: (2026)

Beyond Next Token Prediction: Patch-Level Training for Large Language Models
por: Shao, Chenze, et al.
Publicado: (2024)

Training Language Models via Neural Cellular Automata
por: Lee, Dan, et al.
Publicado: (2026)

Interactive Training: Feedback-Driven Neural Network Optimization
por: Zhang, Wentao, et al.
Publicado: (2025)

Once Upon an Input: Reasoning via Per-Instance Program Synthesis
por: Stein, Adam, et al.
Publicado: (2025)

Towards Efficient Neurally-Guided Program Induction for ARC-AGI
por: Ouellette, Simon
Publicado: (2024)

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis
por: Wei, Anjiang, et al.
Publicado: (2025)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
por: Zhao, Haiyan, et al.
Publicado: (2024)

Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards
por: Padula, Alexander G., et al.
Publicado: (2024)

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
por: Xie, Pei-Xi, et al.
Publicado: (2026)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
por: Zhou, Jin Peng, et al.
Publicado: (2025)

Training a Generally Curious Agent
por: Tajwar, Fahim, et al.
Publicado: (2025)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
por: Mayne, Harry, et al.
Publicado: (2025)

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
por: Gur, Izzeddin, et al.
Publicado: (2023)

AWARE, Beyond Sentence Boundaries: A Contextual Transformer Framework for Identifying Cultural Capital in STEM Narratives
por: Khan, Khalid Mehtab, et al.
Publicado: (2025)

InversionView: A General-Purpose Method for Reading Information from Neural Activations
por: Huang, Xinting, et al.
Publicado: (2024)

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
por: Wei, Anjiang, et al.
Publicado: (2025)

Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation
por: Zhang, Wenbo, et al.
Publicado: (2025)

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
por: Sun, Zhiqing, et al.
Publicado: (2024)

Forking Paths in Neural Text Generation
por: Bigelow, Eric, et al.
Publicado: (2024)

Does Refusal Training in LLMs Generalize to the Past Tense?
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

Symmetry-Constrained Language-Guided Program Synthesis for Discovering Governing Equations from Noisy and Partial Observations
por: Baig, Mirza Samad Ahmed, et al.
Publicado: (2026)

Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
por: Alam, Firoj, et al.
Publicado: (2026)

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
por: Ye, Ziyi, et al.
Publicado: (2024)

Phrase-Level Adversarial Training for Mitigating Bias in Neural Network-based Automatic Essay Scoring
por: Philip, Haddad, et al.
Publicado: (2024)

Training and Evaluating Language Models with Template-based Data Generation
por: Zhang, Yifan
Publicado: (2024)

Post-training an LLM for RAG? Train on Self-Generated Demonstrations
por: Finlayson, Matthew, et al.
Publicado: (2025)

OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
por: Song, Haiyue, et al.
Publicado: (2026)

Tucano: Advancing Neural Text Generation for Portuguese
por: Corrêa, Nicholas Kluge, et al.
Publicado: (2024)

Switchable Decision: Dynamic Neural Generation Networks
por: Zhang, Shujian, et al.
Publicado: (2024)