Imagen de Portada

Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, JoonHo, Woo, Jae Oh, Seok, Juree, Hassanzadeh, Parisa, Jang, Wooseok, Son, JuYoun, Didari, Sima, Gutow, Baruch, Hao, Heng, Moon, Hankyu, Hu, Wenjun, Kwon, Yeong-Dae, Lee, Taehee, Min, Seungjai
Formato:	Preprint
Publicado:	2024
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

Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora
por: Lee, JoonHo, et al.
Publicado: (2024)

Bayesian Active Learning for Semantic Segmentation
por: Didari, Sima, et al.
Publicado: (2024)

PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning
por: Hao, Heng, et al.
Publicado: (2025)

Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
por: Zhou, Zhuoping, et al.
Publicado: (2026)

SGuard-v1: Safety Guardrail for Large Language Models
por: Lee, JoonHo, et al.
Publicado: (2025)

A Bayesian Hierarchical Hurdle Beta-Binomial Model for Survey-Weighted Bounded Counts and Its Application to Childcare Enrollment
por: Lee, JoonHo
Publicado: (2026)

Design-Conditional Prior Elicitation for Dirichlet Process Mixtures: A Unified Framework for Cluster Counts and Weight Control
por: Lee, JoonHo
Publicado: (2026)

Reliability-Targeted Simulation of Item Response Data: Solving the Inverse Design Problem
por: Lee, JoonHo
Publicado: (2025)

Design Effect Ratios for Bayesian Survey Models: A Diagnostic Framework for Identifying Survey-Sensitive Parameters
por: Lee, JoonHo
Publicado: (2026)

Cotype zeta functions enumerating subalgebras of $R$-algebras
por: Lee, Seok Hyeong, et al.
Publicado: (2025)

ViewPCL: a point cloud based active learning method for multi-view segmentation
por: Hilaire, Christian, et al.
Publicado: (2025)

Beyond the Null Effect: Unmasking the True Impact of Teacher-Child Interaction Quality on Child Outcomes in Early Head Start
por: Lee, JoonHo, et al.
Publicado: (2026)

Exploring OCR-augmented Generation for Bilingual VQA
por: Lee, JoonHo, et al.
Publicado: (2025)

Zeta functions of $\mathbb{F}_p$-Lie algebras and finite $p$-groups
por: Lee, Seungjai
Publicado: (2020)

Zeta functions of solvable Lie algebras over finite fields -- with calculations in detail
por: Lee, Seungjai
Publicado: (2026)

Zeta functions of quadratic lattices of a hyperbolic plane
por: Kim, Daejun, et al.
Publicado: (2025)

Zeta functions of quadratic lattices of a hyperbolic plane
por: Daejun Kim, et al.
Publicado: (2025)

Zeta functions enumerating subforms of quadratic forms
por: Kim, Daejun, et al.
Publicado: (2024)

Valid standard errors for Bayesian quantile regression with clustered and independent data
por: Ji, Feng, et al.
Publicado: (2024)

Publish and Perish: How AI-Accelerated Writing Without Proportional Verification Investment Degrades Scientific Knowledge
por: Kwon, Seok Joon
Publicado: (2026)

Computational Design of Optimized Modular Photovoltaic Electrochemical Reactor for Energy Efficient CO2‐to‐Cn Reduction Reaction with Bandgap Tunable Perovskite Tandem Cells
por: Seok Joon Kwon
Publicado: (2024)

Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation
por: Seong, Hyun Seok, et al.
Publicado: (2024)

Gait and cognitive function in the elderly with AD dementia, MCI and healthy
por: Seok Woo Moon
Publicado: (2024)

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements
por: Kwak, SeokJoo, et al.
Publicado: (2025)

XLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering
por: Roh, Keon-Woo, et al.
Publicado: (2025)

V-STRONG: Visual Self-Supervised Traversability Learning for Off-road Navigation
por: Jung, Sanghun, et al.
Publicado: (2023)

Asymmetry and Asynchrony in Postnatal Growth Patterns of Two Sympatric Species of Antarctic Penguins
por: Min‐Su Jeong, et al.
Publicado: (2026)

Factor Analysis of Multivariate Stochastic Volatility Model
por: Lee, Taehee, et al.
Publicado: (2026)

Improving the Estimation of Site-Specific Effects and their Distribution in Multisite Trials
por: Lee, JoonHo, et al.
Publicado: (2023)

Relational Proxy Loss for Audio-Text based Keyword Spotting
por: Jung, Youngmoon, et al.
Publicado: (2024)

On the structure of prime-detecting quasimodular forms in higher levels
por: Kwon, Yeong-Wook, et al.
Publicado: (2026)

Atypical short tandem repeat allelic patterns in a sexual assault case involving hematopoietic stem cell transplantation
por: Jeongyong Kim, et al.
Publicado: (2026)

Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
por: Ju, Yeong-Joon, et al.
Publicado: (2026)

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
por: Ju, Yeong-Joon, et al.
Publicado: (2025)

Quantifying Traffic Patterns with Percolation Theory: A Case Study of Seoul Roads
por: Kwon, Yongsung, et al.
Publicado: (2025)

A Computational Analysis of Traffic Cluster Dynamics Using a Percolation-Based Approach in Urban Road Networks
por: Kwon, Yongsung, et al.
Publicado: (2024)

Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation
por: Ramakrishnan, Aashish Anantha, et al.
Publicado: (2026)

Measurement-based Dynamical Decoupling for Fidelity Preservation on Large-scale Quantum Processors
por: Jae, Jeongwoo, et al.
Publicado: (2025)

FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching
por: Lee, Joongwon, et al.
Publicado: (2025)

Mapping tuberculosis fatalities by region and age group in South Korea: A dataset for targeted health policy optimization
por: Kwon, Yongsung, et al.
Publicado: (2026)