Copertina

PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ghimire, Mukesh, Feng, Aosong, You, Liwen, Luo, Youzhi, Liu, Fang, Zhu, Xuan
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

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

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

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
di: Xu, Ran, et al.
Pubblicazione: (2026)

Learning to Reason without External Rewards
di: Zhao, Xuandong, et al.
Pubblicazione: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
di: Liu, Yixin, et al.
Pubblicazione: (2026)

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

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

Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning
di: Feng, Aosong, et al.
Pubblicazione: (2024)

FreePRM: Training Process Reward Models Without Ground Truth Process Labels
di: Sun, Lin, et al.
Pubblicazione: (2025)

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
di: Xu, Zhichao, et al.
Pubblicazione: (2025)

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

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

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
di: Gao, Jiaxuan, et al.
Pubblicazione: (2026)

Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards
di: Liu, Shuze Daniel, et al.
Pubblicazione: (2026)

Consolidating Rewarded Perturbations for LLM Post-Training
di: Zhang, Zheyu, et al.
Pubblicazione: (2026)

DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs
di: Yin, Lake, et al.
Pubblicazione: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
di: Xu, Hongling, et al.
Pubblicazione: (2025)

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

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
di: Wu, Fang, et al.
Pubblicazione: (2025)

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

PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
di: Lu, Zhixiang, 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)

HAF-RM: A Hybrid Alignment Framework for Reward Model Training
di: Liu, Shujun, et al.
Pubblicazione: (2024)

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

Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards
di: Jia, Ruipeng, et al.
Pubblicazione: (2025)

Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
di: Zhao, Yi, et al.
Pubblicazione: (2025)

RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
di: Yang, Daniel, et al.
Pubblicazione: (2026)

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

AgentV-RL: Scaling Reward Modeling with Agentic Verifier
di: Zhang, Jiazheng, et al.
Pubblicazione: (2026)

Taming Overconfidence in LLMs: Reward Calibration in RLHF
di: Leng, Jixuan, et al.
Pubblicazione: (2024)

TaeBench: Improving Quality of Toxic Adversarial Examples
di: Zhu, Xuan, et al.
Pubblicazione: (2024)

DORA Explorer: Improving the Exploration Ability of LLMs Without Training
di: Gurjar, Priya, et al.
Pubblicazione: (2026)

CAMEL: Confidence-Gated Reflection for Reward Modeling
di: Zhu, Zirui, et al.
Pubblicazione: (2026)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
di: Wang, Peisong, et al.
Pubblicazione: (2025)

TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment
di: Kim, Taesoo, et al.
Pubblicazione: (2025)

RRM: Robust Reward Model Training Mitigates Reward Hacking
di: Liu, Tianqi, et al.
Pubblicazione: (2024)

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
di: Yu, Qinan, et al.
Pubblicazione: (2026)

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

Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
di: Liu, Chris Yuhao, et al.
Pubblicazione: (2024)

Sotopia-RL: Reward Design for Social Intelligence
di: Yu, Haofei, et al.
Pubblicazione: (2025)