Copertina

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Qinan, Tartaglini, Alexa, Hase, Peter, Guestrin, Carlos, Potts, Christopher
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
di: Hase, Peter, et al.
Pubblicazione: (2026)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
di: Tartaglini, Alexa R., et al.
Pubblicazione: (2025)

The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations
di: Worledge, Theodora, et al.
Pubblicazione: (2024)

Improved Representation Steering for Language Models
di: Wu, Zhengxuan, et al.
Pubblicazione: (2025)

Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning
di: Pronesti, Massimiliano, et al.
Pubblicazione: (2026)

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
di: Liu, Shudong, et al.
Pubblicazione: (2025)

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
di: Wang, Binghai, et al.
Pubblicazione: (2026)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
di: Su, Yi, et al.
Pubblicazione: (2025)

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
di: Setlur, Amrith, et al.
Pubblicazione: (2024)

Discovering Implicit Large Language Model Alignment Objectives
di: Chen, Edward, et al.
Pubblicazione: (2026)

Benchmarking Distributional Alignment of Large Language Models
di: Meister, Nicole, et al.
Pubblicazione: (2024)

Base Models Beat Aligned Models at Randomness and Creativity
di: West, Peter, et al.
Pubblicazione: (2025)

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
di: Stojanovski, Zafir, et al.
Pubblicazione: (2025)

metaTextGrad: Automatically optimizing language model optimizers
di: Xu, Guowei, et al.
Pubblicazione: (2025)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
di: Wen, Xumeng, et al.
Pubblicazione: (2025)

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
di: Jiang, Yuxin, et al.
Pubblicazione: (2026)

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
di: Wang, Xiangfeng, et al.
Pubblicazione: (2026)

Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
di: Boguraev, Sasha, et al.
Pubblicazione: (2025)

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
di: Liu, Xiaoyuan, et al.
Pubblicazione: (2025)

Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models
di: Han, Mingyue, et al.
Pubblicazione: (2021)

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
di: Lyu, Chengqi, et al.
Pubblicazione: (2025)

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
di: Chen, Ding, et al.
Pubblicazione: (2025)

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
di: Wu, Zhengxuan, et al.
Pubblicazione: (2023)

Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
di: Lara, Luis, et al.
Pubblicazione: (2026)

Rely-Guarantee Reasoning for Causally Consistent Shared Memory (Extended Version)
di: Lahav, Ori, et al.
Pubblicazione: (2023)

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
di: Ren, Mengjie, et al.
Pubblicazione: (2026)

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
di: Tang, Xinyu, et al.
Pubblicazione: (2025)

Lessons from Training Grounded LLMs with Verifiable Rewards
di: Sim, Shang Hong, et al.
Pubblicazione: (2025)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
di: Ma, Zhengzhao, et al.
Pubblicazione: (2026)

Logical Reasoning with Outcome Reward Models for Test-Time Scaling
di: Thatikonda, Ramya Keerthy, et al.
Pubblicazione: (2025)

Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning
di: Yu, Fei, et al.
Pubblicazione: (2025)

CausalGym: Benchmarking causal interpretability methods on linguistic tasks
di: Arora, Aryaman, et al.
Pubblicazione: (2024)

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
di: Guo, Xu, et al.
Pubblicazione: (2025)

RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
di: Wang, Zongsheng, et al.
Pubblicazione: (2025)

Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees
di: Ali, Mohammed Himayath, et al.
Pubblicazione: (2026)

Long Is More Important Than Difficult for Training Reasoning Models
di: Shen, Si, et al.
Pubblicazione: (2025)

Reward Reasoning Model
di: Guo, Jiaxin, et al.
Pubblicazione: (2025)

I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers
di: Tartaglini, Alexa R., et al.
Pubblicazione: (2026)

A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
di: Wachi, Akifumi, et al.
Pubblicazione: (2026)

A paradox of AI fluency
di: Potts, Christopher, et al.
Pubblicazione: (2026)