Imagen de Portada

Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiong, Zidi, Chen, Shan, Lakkaraju, Himabindu
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
por: Xiong, Zidi, et al.
Publicado: (2025)

Learning Recourse Costs from Pairwise Feature Comparisons
por: Rawal, Kaivalya, et al.
Publicado: (2024)

In-Context Unlearning: Language Models as Few Shot Unlearners
por: Pawelczyk, Martin, et al.
Publicado: (2023)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
por: Zhang, Shichang, et al.
Publicado: (2025)

Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
por: Zhang, Shichang, et al.
Publicado: (2025)

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers
por: Oesterling, Alex, et al.
Publicado: (2024)

Generalized Group Data Attribution
por: Ley, Dan, et al.
Publicado: (2024)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
por: Pawelczyk, Martin, et al.
Publicado: (2024)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
por: Li, Aaron J., et al.
Publicado: (2025)

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
por: Krishna, Satyapriya, et al.
Publicado: (2022)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
por: Lobo, Elita, et al.
Publicado: (2024)

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models
por: Kroeger, Nicholas, et al.
Publicado: (2023)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
por: Huang, Kexin, et al.
Publicado: (2026)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
por: Du, Hongzhe, et al.
Publicado: (2025)

How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
por: Xiong, Zidi, et al.
Publicado: (2025)

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
por: Wu, Junkang, et al.
Publicado: (2025)

Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
por: Bhalla, Usha, et al.
Publicado: (2025)

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
por: Qi, Zhenting, et al.
Publicado: (2024)

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
por: Huang, Zhuoxu, et al.
Publicado: (2026)

OpenXAI: Towards a Transparent Evaluation of Model Explanations
por: Agarwal, Chirag, et al.
Publicado: (2022)

Generalization of RLVR Using Causal Reasoning as a Testbed
por: Lu, Brian, et al.
Publicado: (2025)

Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVR
por: Ingle, Yash, et al.
Publicado: (2026)

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
por: Yang, Zhicheng, et al.
Publicado: (2025)

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
por: Mao, Yixiu, et al.
Publicado: (2026)

Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
por: Bounhar, Abdelaziz, et al.
Publicado: (2025)

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
por: Mitsuhashi, Ryo, et al.
Publicado: (2026)

Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
por: Qiu, Zhongxi, et al.
Publicado: (2025)

Certifying LLM Safety against Adversarial Prompting
por: Kumar, Aounon, et al.
Publicado: (2023)

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
por: Duo, Jiangshan, et al.
Publicado: (2026)

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
por: Wu, Tianyu, et al.
Publicado: (2026)

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
por: Hao, Zhezheng, et al.
Publicado: (2025)

Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR
por: Mou, Chaoli, et al.
Publicado: (2026)

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
por: Yao, Xinhao, et al.
Publicado: (2025)

A Study on the Calibration of In-context Learning
por: Zhang, Hanlin, et al.
Publicado: (2023)

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
por: Xie, Pei-Xi, et al.
Publicado: (2026)

VL Norm: Rethink Loss Aggregation in RLVR
por: He, Zhiyuan, et al.
Publicado: (2025)

Spurious Rewards: Rethinking Training Signals in RLVR
por: Shao, Rulin, et al.
Publicado: (2025)

A State-of-the-Art SQL Reasoning Model using RLVR
por: Ali, Alnur, et al.
Publicado: (2025)

Manipulating Large Language Models to Increase Product Visibility
por: Kumar, Aounon, et al.
Publicado: (2024)

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
por: Lu, Han, et al.
Publicado: (2025)