Cover Image

ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jung, Jeesu, Park, Chanjun, Jung, Sangkeun
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Domain Robust Lightweight Reward Models based on Router Mechanism
by: Namgoong, Hyuk, et al.
Published: (2024)

LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis
by: Heo, Inbum, et al.
Published: (2026)

InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasets
by: Kim, Yungi, et al.
Published: (2024)

CoME: An Unlearning-based Approach to Conflict-free Model Editing
by: Jung, Dahyun, et al.
Published: (2025)

FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
by: Jung, Dahyun, et al.
Published: (2025)

Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
by: Lee, Seungyoon, et al.
Published: (2024)

Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
by: Feng, Duanyu, et al.
Published: (2024)

Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard
by: Park, Chanjun, et al.
Published: (2024)

Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis
by: Lee, Nayeon, et al.
Published: (2023)

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism
by: Park, Chanjun, et al.
Published: (2024)

Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMs
by: Jung, Jeesu, et al.
Published: (2025)

ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
by: Park, Jeiyoon, et al.
Published: (2024)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
by: Park, Jeiyoon, et al.
Published: (2024)

KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
by: Kim, Dongjun, et al.
Published: (2025)

Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity Recognition
by: Kang, Hyeonseok, et al.
Published: (2024)

MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
by: Park, Chanhee, et al.
Published: (2025)

Sensory-Aware Sequential Recommendation via Review-Distilled Representations
by: Yoon, Yeo Chan, et al.
Published: (2026)

Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero-Data-Leakage Setting
by: Pyeon, Goun, et al.
Published: (2025)

Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models
by: Park, Hyunbyung, et al.
Published: (2024)

Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models
by: Kim, Dahyun, et al.
Published: (2024)

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
by: Shin, Joongmin, et al.
Published: (2026)

Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning
by: Kim, Jeonghoon, et al.
Published: (2024)

MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs
by: Hwang, Yerin, et al.
Published: (2024)

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
by: Choi, Juhwan, et al.
Published: (2024)

Evalverse: Unified and Accessible Library for Large Language Model Evaluation
by: Kim, Jihoo, et al.
Published: (2024)

System Message Generation for User Preferences using Open-Source Models
by: Jeong, Minbyul, et al.
Published: (2025)

LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis
by: Heo, Inbum, et al.
Published: (2025)

LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models
by: Kim, Yungi, et al.
Published: (2024)

Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora
by: Kim, Yungi, et al.
Published: (2024)

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
by: Jang, Youngjoon, et al.
Published: (2025)

Personalized LLM Decoding via Contrasting Personal Preference
by: Bu, Hyungjune, et al.
Published: (2025)

Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Education
by: Yang, Rui, et al.
Published: (2024)

TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
by: Jung, Chanjoo, et al.
Published: (2025)

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models
by: Liu, Fengchen, et al.
Published: (2024)

VPO: Leveraging the Number of Votes in Preference Optimization
by: Cho, Jae Hyeon, et al.
Published: (2024)

SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
by: Kim, Hyeonwoo, et al.
Published: (2024)

HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models
by: Gao, Fan, et al.
Published: (2025)

1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models
by: Park, Chanjun, et al.
Published: (2024)

CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer
by: Jung, Heeseok, et al.
Published: (2024)

From Patient Consultations to Graphs: Leveraging LLMs for Patient Journey Knowledge Graph Construction
by: Khatib, Hassan S. Al, et al.
Published: (2025)