Copertina

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bakman, Yavuz, Kang, Sungmin, Huang, Zhiqi, Yaldiz, Duygu Nur, Belém, Catarina G., Zhu, Chenyang, Kumar, Anoop, Samuel, Alfy, Avestimehr, Salman, Liu, Daben, Karimireddy, Sai Praneeth
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
di: Bakman, Yavuz, et al.
Pubblicazione: (2026)

Reconsidering LLM Uncertainty Estimation Methods in the Wild
di: Bakman, Yavuz, et al.
Pubblicazione: (2025)

Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
di: Kang, Sungmin, et al.
Pubblicazione: (2025)

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
di: Yaldiz, Duygu Nur, et al.
Pubblicazione: (2025)

Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
di: Ziashahabi, Amir, et al.
Pubblicazione: (2025)

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
di: Bakman, Yavuz Faruk, et al.
Pubblicazione: (2024)

Conformal Prediction Adaptive to Unknown Subpopulation Shifts
di: Wang, Nien-Shao, et al.
Pubblicazione: (2025)

Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements
di: Oguz, Metehan, et al.
Pubblicazione: (2025)

Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
di: Yaldiz, Duygu Nur, et al.
Pubblicazione: (2024)

CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
di: Mushtaq, Erum, et al.
Pubblicazione: (2024)

Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
di: Huang, Zhiqi, et al.
Pubblicazione: (2025)

Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics
di: Belem, Catarina G, et al.
Pubblicazione: (2025)

HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models
di: Mushtaq, Erum, et al.
Pubblicazione: (2025)

FB-RAG: Improving RAG with Forward and Backward Lookup
di: Chawla, Kushal, et al.
Pubblicazione: (2025)

A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
di: Lawton, Neal Gregory, et al.
Pubblicazione: (2025)

Uncertainty Quantification in Retrieval Augmented Question Answering
di: Perez-Beltrachini, Laura, et al.
Pubblicazione: (2025)

Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards
di: Hamman, Faisal, et al.
Pubblicazione: (2025)

Optimization with Access to Auxiliary Information
di: Chayti, El Mahdi, et al.
Pubblicazione: (2022)

EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
di: Banayeeanzade, Amin, et al.
Pubblicazione: (2026)

Epistemic Wrapping for Uncertainty Quantification
di: Sultana, Maryam, et al.
Pubblicazione: (2025)

Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs
di: Glenn, Parker, et al.
Pubblicazione: (2025)

LLM Optimization Unlocks Real-Time Pairwise Reranking
di: Wu, Jingyu, et al.
Pubblicazione: (2025)

On the Limits of Momentum in Decentralized and Federated Optimization
di: Zaccone, Riccardo, et al.
Pubblicazione: (2025)

Leveraging Uncertainty Estimation for Efficient LLM Routing
di: Zhang, Tuo, et al.
Pubblicazione: (2025)

Improving Metacognition and Uncertainty Communication in Language Models
di: Steyvers, Mark, et al.
Pubblicazione: (2025)

Label-wise Aleatoric and Epistemic Uncertainty Quantification
di: Sale, Yusuf, et al.
Pubblicazione: (2024)

GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
di: Kang, Sungmin, et al.
Pubblicazione: (2025)

Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
di: Guo, Tianyu, et al.
Pubblicazione: (2024)

Defection-Free Collaboration between Competitors in a Learning System
di: Werner, Mariel, et al.
Pubblicazione: (2024)

Do Data Valuations Make Good Data Prices?
di: Fan, Dongyang, et al.
Pubblicazione: (2025)

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
di: Jain, Neel, et al.
Pubblicazione: (2024)

Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering
di: Liu, Yaokun, et al.
Pubblicazione: (2026)

Epistemic and Aleatoric Uncertainty Quantification in Weather and Climate Models
di: Mansfield, Laura A., et al.
Pubblicazione: (2025)

Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
di: Zepf, Kilian, et al.
Pubblicazione: (2023)

Epistemic Uncertainty Quantification For Pre-trained Neural Network
di: Wang, Hanjing, et al.
Pubblicazione: (2024)

LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
di: Rokvic, Ljubomir, et al.
Pubblicazione: (2022)

Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum
di: Zaccone, Riccardo, et al.
Pubblicazione: (2023)

Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
di: Fan, Dongyang, et al.
Pubblicazione: (2025)

A Differentially Private Kaplan-Meier Estimator for Privacy-Preserving Survival Analysis
di: Veeraragavan, Narasimha Raghavan, et al.
Pubblicazione: (2024)

Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
di: Hu, Mengxuan, et al.
Pubblicazione: (2026)