Imagen de Portada

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Zae Myung, Park, Chanwoo, Raheja, Vipul, Kim, Suin, Kang, Dongyeop
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Amazing Agent Race: Strong Tool Users, Weak Navigators
por: Kim, Zae Myung, et al.
Publicado: (2026)

Benchmarking Cognitive Biases in Large Language Models as Evaluators
por: Koo, Ryan, et al.
Publicado: (2023)

Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs
por: Kim, Zae Myung, et al.
Publicado: (2024)

Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
por: Lee, Minhwa, et al.
Publicado: (2024)

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output
por: Mooney, James, et al.
Publicado: (2026)

Align to Structure: Aligning Large Language Models with Structural Information
por: Kim, Zae Myung, et al.
Publicado: (2025)

ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models
por: Li, Jierui, et al.
Publicado: (2023)

Spivavtor: An Instruction Tuned Ukrainian Text Editing Model
por: Saini, Aman, et al.
Publicado: (2024)

LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech
por: Kim, Haechan, et al.
Publicado: (2024)

Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
por: Mooney, James, et al.
Publicado: (2025)

Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation
por: de Langis, Karin, et al.
Publicado: (2024)

Personalized Text Generation with Fine-Grained Linguistic Control
por: Alhafni, Bashar, et al.
Publicado: (2024)

Learning Explainable Dense Reward Shapes via Bayesian Optimization
por: Koo, Ryan, et al.
Publicado: (2025)

Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
por: Lee, Unggi, et al.
Publicado: (2026)

Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations
por: Jeong, Minoh, et al.
Publicado: (2024)

APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification
por: Chernodub, Artem, et al.
Publicado: (2025)

SelectLLM: Can LLMs Select Important Instructions to Annotate?
por: Parkar, Ritik Sachin, et al.
Publicado: (2024)

Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes
por: de Langis, Karin, et al.
Publicado: (2025)

Becoming Experienced Judges: Selective Test-Time Learning for Evaluators
por: Jwa, Seungyeon, et al.
Publicado: (2025)

Process Reward Models That Think
por: Khalifa, Muhammad, et al.
Publicado: (2025)

Extractive text summarisation of Privacy Policy documents using machine learning approaches
por: Choi, Chanwoo
Publicado: (2024)

MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models
por: Son, Guijin, et al.
Publicado: (2024)

Enhancing Document-Level Machine Translation via Filtered Synthetic Corpora and Two-Stage LLM Adaptation
por: Kim, Ireh, et al.
Publicado: (2026)

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
por: Kim, Sunghwan, et al.
Publicado: (2025)

PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory
por: Myung, Junho, et al.
Publicado: (2025)

II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering
por: Kil, Jihyung, et al.
Publicado: (2024)

Under the Surface: Tracking the Artifactuality of LLM-Generated Data
por: Das, Debarati, et al.
Publicado: (2024)

Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources
por: Kim, Jinpyo, et al.
Publicado: (2025)

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction
por: Lee, Yooseop, et al.
Publicado: (2025)

InvThink: Premortem Reasoning for Safer Language Models
por: Kim, Yubin, et al.
Publicado: (2025)

mEdIT: Multilingual Text Editing via Instruction Tuning
por: Raheja, Vipul, et al.
Publicado: (2024)

From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models
por: Raheja, Tarun, et al.
Publicado: (2026)

Beyond Line-Level Filtering for the Pretraining Corpora of LLMs
por: Park, Chanwoo, et al.
Publicado: (2025)

HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition
por: Paik, Gio, et al.
Publicado: (2025)

Discriminative Policy Optimization for Token-Level Reward Models
por: Chen, Hongzhan, et al.
Publicado: (2025)

Evaluating Robustness of Reward Models for Mathematical Reasoning
por: Kim, Sunghwan, et al.
Publicado: (2024)

Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean
por: Park, Chanwoo, et al.
Publicado: (2025)

Bridging Symbolic Control and Neural Reasoning in LLM Agents: Structured Cognitive Loop with a Governance Layer
por: Kim, Myung Ho
Publicado: (2025)

Can Large Language Models Differentiate Harmful from Argumentative Essays? Steps Toward Ethical Essay Scoring
por: Kim, Hongjin, et al.
Publicado: (2026)

How Far Can We Extract Diverse Perspectives from Large Language Models?
por: Hayati, Shirley Anugrah, et al.
Publicado: (2023)