Imagen de Portada

When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Galeone, Cosimo, Park, Minsu, Ettorre, Giuseppe, Ligorio, Daniele
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
por: Xu, Xiaoyu, et al.
Publicado: (2025)

When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
por: Mustaqim, S. M., et al.
Publicado: (2025)

Inverse Scaling: When Bigger Isn't Better
por: McKenzie, Ian R., et al.
Publicado: (2023)

Why Isn't Relational Learning Taking Over the World?
por: Poole, David
Publicado: (2025)

SLOT: Structuring the Output of Large Language Models
por: Wang, Darren Yow-Bang, et al.
Publicado: (2025)

Domain-Adapted Small Language Models for Reliable Clinical Triage
por: Aljohani, Manar, et al.
Publicado: (2026)

When Fairness Isn't Statistical: The Limits of Machine Learning in Evaluating Legal Reasoning
por: Barale, Claire, et al.
Publicado: (2025)

Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
por: Ethayarajh, Kawin, et al.
Publicado: (2021)

Clarify: Improving Model Robustness With Natural Language Corrections
por: Lee, Yoonho, et al.
Publicado: (2024)

Structured Prompts Improve Evaluation of Language Models
por: Aali, Asad, et al.
Publicado: (2025)

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
por: Barkett, Emilio, et al.
Publicado: (2025)

The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models
por: Cho, Seonglae, et al.
Publicado: (2026)

An Evaluation on Large Language Model Outputs: Discourse and Memorization
por: de Wynter, Adrian, et al.
Publicado: (2023)

Leviathan: Decoupling Input and Output Representations in Language Models
por: Batley, Reza T., et al.
Publicado: (2026)

Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
por: Pan, Rui, et al.
Publicado: (2025)

Improving Language Models with Intentional Analysis
por: Yin, Yuwei, et al.
Publicado: (2025)

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
por: Zhao, Stephen, et al.
Publicado: (2025)

Graph-based Uncertainty Metrics for Long-form Language Model Outputs
por: Jiang, Mingjian, et al.
Publicado: (2024)

Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
por: Anschel, Oron, et al.
Publicado: (2025)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
por: Zhang, Yue, et al.
Publicado: (2026)

Integrating Locality-Aware Attention with Transformers for General Geometry PDEs
por: Koh, Minsu, et al.
Publicado: (2025)

Reliable, Adaptable, and Attributable Language Models with Retrieval
por: Asai, Akari, et al.
Publicado: (2024)

Context Dependence and Reliability in Autoregressive Language Models
por: Sengupta, Poushali, et al.
Publicado: (2026)

Stacking Small Language Models for Generalizability
por: Liang, Laurence
Publicado: (2024)

All Language Models Large and Small
por: Chen, Zhixun, et al.
Publicado: (2024)

Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
por: Fadeeva, Ekaterina, et al.
Publicado: (2024)

Kakugo: Distillation of Low-Resource Languages into Small Language Models
por: Devine, Peter, et al.
Publicado: (2026)

Curriculum Learning for Small Code Language Models
por: Naïr, Marwa, et al.
Publicado: (2024)

Small Language Models: Survey, Measurements, and Insights
por: Lu, Zhenyan, et al.
Publicado: (2024)

Towards Reasoning Ability of Small Language Models
por: Srivastava, Gaurav, et al.
Publicado: (2025)

Squat: Quant Small Language Models on the Edge
por: Shen, Xuan, et al.
Publicado: (2024)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
por: Bouchard, Dylan, et al.
Publicado: (2026)

A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs
por: Watts, Jake R., et al.
Publicado: (2024)

Improving Large Models with Small models: Lower Costs and Better Performance
por: Chen, Dong, et al.
Publicado: (2024)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
por: Sinha, Neelabh, et al.
Publicado: (2024)

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
por: Cho, Junmo, et al.
Publicado: (2026)

When Attention Sink Emerges in Language Models: An Empirical View
por: Gu, Xiangming, et al.
Publicado: (2024)

PairBench: Are Vision-Language Models Reliable at Comparing What They See?
por: Feizi, Aarash, et al.
Publicado: (2025)

Phase Transitions in the Output Distribution of Large Language Models
por: Arnold, Julian, et al.
Publicado: (2024)

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
por: Goren, Shani, et al.
Publicado: (2026)