Imagen de Portada

Think Twice: Branch-and-Rethink Reasoning Reward Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiao, Yizhu, Zeng, Jiaqi, Vialard, Julien Veron, Kuchaiev, Oleksii, Han, Jiawei, Delalleau, Olivier
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

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
por: Wang, Zhilin, et al.
Publicado: (2025)

HelpSteer2-Preference: Complementing Ratings with Preferences
por: Wang, Zhilin, et al.
Publicado: (2024)

GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning
por: Ficek, Aleksander, et al.
Publicado: (2024)

Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment
por: Sun, Shengyang, et al.
Publicado: (2025)

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
por: Wang, Zhilin, et al.
Publicado: (2025)

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
por: Wang, Zhilin, et al.
Publicado: (2025)

HelpSteer2: Open-source dataset for training top-performing reward models
por: Wang, Zhilin, et al.
Publicado: (2024)

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
por: Tian, Xiaoyu, et al.
Publicado: (2025)

NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
por: Shen, Gerald, et al.
Publicado: (2024)

Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
por: Renduchintala, Adithya, et al.
Publicado: (2023)

TEXT2DB: Integration-Aware Information Extraction with Large Language Model Agents
por: Jiao, Yizhu, et al.
Publicado: (2025)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
por: Lacombe, Romain, et al.
Publicado: (2025)

Establishing Knowledge Preference in Language Models
por: Zhou, Sizhe, et al.
Publicado: (2024)

Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events
por: Kargupta, Priyanka, et al.
Publicado: (2024)

A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
por: Jiang, Pengcheng, 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)

Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection
por: Jana, Soumyadeep, et al.
Publicado: (2025)

Adversarial Training of Reward Models
por: Bukharin, Alexander, et al.
Publicado: (2025)

Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
por: He, Jiashu, et al.
Publicado: (2026)

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
por: Mikula, Lukáš, et al.
Publicado: (2023)

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection
por: Phan, Hoang, et al.
Publicado: (2025)

Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction
por: Zubillaga, Mikel, et al.
Publicado: (2026)

Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
por: Li, Moxin, et al.
Publicado: (2024)

Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
por: Jiao, Yizhu, et al.
Publicado: (2026)

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards
por: Su, Jinyan, et al.
Publicado: (2025)

Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
por: Qian, Yushan, et al.
Publicado: (2023)

Investigating Instruction Tuning Large Language Models on Graphs
por: Zhu, Kerui, et al.
Publicado: (2024)

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
por: Sun, Jiashuo, et al.
Publicado: (2026)

Reward Reasoning Model
por: Guo, Jiaxin, et al.
Publicado: (2025)

Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series
por: Cai, Wenrui, et al.
Publicado: (2025)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
por: Tang, Yao, et al.
Publicado: (2026)

Libra: Assessing and Improving Reward Model by Learning to Think
por: Zhou, Meng, et al.
Publicado: (2025)

Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
por: Tang, Fei, et al.
Publicado: (2025)

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

Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
por: Wang, Xinpeng, et al.
Publicado: (2025)

Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
por: Du, Hanwen, et al.
Publicado: (2025)

Thinking Out Loud: Do Reasoning Models Know When They're Right?
por: Zeng, Qingcheng, et al.
Publicado: (2025)

Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
por: Gan, Zeyu, et al.
Publicado: (2025)

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding
por: Yang, Jianjiang, et al.
Publicado: (2025)

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