Cover Image

Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zongxia, Chang, Yapei, Zhou, Yuhang, Wu, Xiyang, Liang, Zichao, Sung, Yoo Yeon, Boyd-Graber, Jordan Lee
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation
by: Sung, Yoo Yeon, et al.
Published: (2024)

CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering
by: Li, Zongxia, et al.
Published: (2024)

Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness
by: Sung, Yoo Yeon, et al.
Published: (2024)

GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration
by: Sung, Yoo Yeon, et al.
Published: (2025)

PEDANTS: Cheap but Effective and Interpretable Answer Equivalence
by: Li, Zongxia, et al.
Published: (2024)

AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?
by: Gor, Maharshi, et al.
Published: (2026)

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
by: Li, Zongxia, et al.
Published: (2025)

SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement
by: Mondal, Ishani, et al.
Published: (2024)

Self-Rewarding Vision-Language Model via Reasoning Decomposition
by: Li, Zongxia, et al.
Published: (2025)

Large Language Models Are Effective Human Annotation Assistants, But Not Good Independent Annotators
by: Gu, Feng, et al.
Published: (2025)

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users
by: Balepur, Nishant, et al.
Published: (2025)

Prompt-Level Reward Specifications for Open-Ended Post-Training
by: Weng, Zijun, et al.
Published: (2026)

KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students
by: Shu, Matthew, et al.
Published: (2024)

Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above
by: Balepur, Nishant, et al.
Published: (2025)

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
by: Yang, Zixuan, et al.
Published: (2026)

DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering
by: Srikanth, Neha, et al.
Published: (2026)

Labeled Interactive Topic Models
by: Seelman, Kyle, et al.
Published: (2023)

G-Zero: Self-Play for Open-Ended Generation from Zero Data
by: Huang, Chengsong, et al.
Published: (2026)

Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis
by: Li, Zongxia, et al.
Published: (2024)

Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of Topic Models
by: Li, Zongxia, et al.
Published: (2025)

Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA
by: Gor, Maharshi, et al.
Published: (2024)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
by: Ye, Zhiling, et al.
Published: (2025)

Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
by: Samuel, Vinay, et al.
Published: (2026)

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
by: Lin, Zhiwei, et al.
Published: (2024)

NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization
by: Zhang, Zheyuan, et al.
Published: (2025)

Argument Collapse: LLMs Flatten Long-Form Public Debate
by: Kim, Yekyung, et al.
Published: (2026)

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation
by: Guo, Zhihan, et al.
Published: (2025)

From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset
by: Yoo, Haneul, et al.
Published: (2026)

Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation
by: Cao, Guining, et al.
Published: (2026)

AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
by: Wu, Xiyang, et al.
Published: (2024)

Scattered Hypothesis Generation for Open-Ended Event Forecasting
by: Chang, He, et al.
Published: (2026)

SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity
by: Mondal, Ishani, et al.
Published: (2025)

CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding
by: Mondal, Ishani, et al.
Published: (2026)

Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
by: Prasad, Aaditya Vikram, et al.
Published: (2026)

ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering
by: Hoyle, Alexander, et al.
Published: (2025)

Reverse-Engineered Reasoning for Open-Ended Generation
by: Wang, Haozhe, et al.
Published: (2025)

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
by: Choi, Hyeong Kyu, et al.
Published: (2026)

OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation
by: Zhang, Hanning, et al.
Published: (2025)

Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning
by: Zhang, Zheng, et al.
Published: (2026)

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
by: Liu, Dawei, et al.
Published: (2026)