Imagen de Portada

The Anatomy of Uncertainty in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Taparia, Aditya, Senanayake, Ransalu, Thopalli, Kowshik, Narayanaswamy, Vivek
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Robustness In Sparse Autoencoders via Masked Regularization
por: Narayanaswamy, Vivek, et al.
Publicado: (2026)

The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning
por: Senanayake, Ransalu
Publicado: (2024)

ExpressivityBench: Can LLMs Communicate Implicitly?
por: Tint, Joshua, et al.
Publicado: (2024)

Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
por: Sagar, Som, et al.
Publicado: (2024)

LLM-Assisted Red Teaming of Diffusion Models through "Failures Are Fated, But Can Be Faded"
por: Sagar, Som, et al.
Publicado: (2024)

Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
por: Taparia, Aditya, et al.
Publicado: (2024)

Towards Adapting Reinforcement Learning Agents to New Tasks: Insights from Q-Values
por: Ramaswamy, Ashwin, et al.
Publicado: (2024)

LLM Routing as Reasoning: A MaxSAT View
por: Nguyen, Son, et al.
Publicado: (2026)

PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
por: Gundawar, Atharva, et al.
Publicado: (2025)

ProtAlign: Contrastive learning paradigm for Sequence and structure alignment
por: Ranganath, Aditya, et al.
Publicado: (2026)

DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation
por: Subramanyam, Rakshith, et al.
Publicado: (2024)

The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
por: Onyame, Eric, et al.
Publicado: (2026)

HPix: Generating Vector Maps from Satellite Images
por: Taparia, Aditya, et al.
Publicado: (2024)

BaTCAVe: Trustworthy Explanations for Robot Behaviors
por: Sagar, Som, et al.
Publicado: (2024)

Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments
por: Leiva, Mario, et al.
Publicado: (2025)

On the Use of Anchoring for Training Vision Models
por: Narayanaswamy, Vivek, et al.
Publicado: (2024)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
por: Kulkarni, Akshay, et al.
Publicado: (2025)

CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs
por: Kowshik, Suhas S, et al.
Publicado: (2024)

Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions
por: Chen, Edward, et al.
Publicado: (2024)

Automated Consistency Analysis of LLMs
por: Patwardhan, Aditya, et al.
Publicado: (2025)

Speeding Up Image Classifiers with Little Companions
por: Liu, Yang, et al.
Publicado: (2024)

Leveraging Registers in Vision Transformers for Robust Adaptation
por: Yellapragada, Srikar, et al.
Publicado: (2025)

Multiple Distribution Shift -- Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation
por: Ngu, Noel, et al.
Publicado: (2025)

Feature Importance Guided Random Forest Learning with Simulated Annealing Based Hyperparameter Tuning
por: Balasubramanian, Kowshik, et al.
Publicado: (2025)

How Good LLM-Generated Password Policies Are?
por: Vaidya, Vivek, et al.
Publicado: (2025)

Towards Reliable Alignment: Uncertainty-aware RLHF
por: Banerjee, Debangshu, et al.
Publicado: (2024)

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs
por: Ferdous, K M, et al.
Publicado: (2026)

CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
por: Nguyen, Son, et al.
Publicado: (2026)

Viewpoint-Agnostic Manipulation Policies with Strategic Vantage Selection
por: Vasudevan, Sreevishakh, et al.
Publicado: (2025)

Fairness in Autonomous Driving: Towards Understanding Confounding Factors in Object Detection under Challenging Weather
por: Pathiraja, Bimsara, et al.
Publicado: (2024)

SEAL: Suite for Evaluating API-use of LLMs
por: Kim, Woojeong, et al.
Publicado: (2024)

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
por: Yan, Xinyuan, et al.
Publicado: (2025)

Towards Reliable, Uncertainty-Aware Alignment
por: Banerjee, Debangshu, et al.
Publicado: (2025)

Uncertainty-Guided Coarse-to-Fine Tumor Segmentation with Anatomy-Aware Post-Processing
por: Isler, Ilkin Sevgi, et al.
Publicado: (2025)

Graph-Eq: Discovering Mathematical Equations using Graph Generative Models
por: Ranasinghe, Nisal, et al.
Publicado: (2025)

VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection
por: Taparia, Aditya, et al.
Publicado: (2025)

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
por: Kaur, Ramneet, et al.
Publicado: (2024)

MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
por: Yang, Yongjin, et al.
Publicado: (2024)

Unequal Voices: How LLMs Construct Constrained Queer Narratives
por: Ghosal, Atreya, et al.
Publicado: (2025)

Synapse Compendium Aware Federated Knowledge Exchange for Tool Routed LLMs
por: Chakraborty, Abhijit, et al.
Publicado: (2026)