Image de couverture de livre

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yidong, Wang, Xin, Wang, Cunxiang, Fang, Junfeng, Wang, Qiufeng, Chu, Jianing, Meng, Xuran, Yang, Shuxun, Qin, Libo, Zhang, Yue, Ye, Wei, Zhang, Shikun
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RewardAnything: Generalizable Principle-Following Reward Models
par: Yu, Zhuohao, et autres
Publié: (2025)

TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
par: Wang, Yidong, et autres
Publié: (2025)

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
par: Yu, Zhuohao, et autres
Publié: (2024)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
par: Feng, Andrew Zhuoer, et autres
Publié: (2026)

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
par: Zhang, Jinyang, et autres
Publié: (2025)

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
par: Wang, Yidong, et autres
Publié: (2023)

CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
par: Zeng, Zhengran, et autres
Publié: (2024)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
par: Liu, Yang, et autres
Publié: (2026)

Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
par: Li, Bo, et autres
Publié: (2026)

Nash CoT: Multi-Path Inference with Preference Equilibrium
par: Zhang, Ziqi, et autres
Publié: (2024)

FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
par: Yu, Zhuohao, et autres
Publié: (2024)

KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models
par: Yu, Zhuohao, et autres
Publié: (2024)

UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge
par: Zhang, Yang, et autres
Publié: (2025)

Deep Literature Survey Automation with an Iterative Workflow
par: Zhang, Hongbo, et autres
Publié: (2025)

DRAFT: Task Decoupled Latent Reasoning for Agent Safety
par: Wang, Lin, et autres
Publié: (2026)

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
par: Jiang, Shuyang, et autres
Publié: (2025)

Chosen Peoples
par: Tounsel, Christopher
Publié: (2021)

Temporally Decoupled Diffusion Planning for Autonomous Driving
par: Li, Xiang, et autres
Publié: (2026)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
par: Wen, Bosi, et autres
Publié: (2026)

StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
par: Yang, Shu-Xun, et autres
Publié: (2025)

Spatio-temporal Multivariate Time Series Forecast with Chosen Variables
par: Liu, Zibo, et autres
Publié: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
par: Bao, Guangsheng, et autres
Publié: (2024)

Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
par: Wang, Yuan, et autres
Publié: (2026)

Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization
par: Meng, Xuran, et autres
Publié: (2024)

Towards Understanding Feature Learning in Parameter Transfer
par: Yuan, Hua, et autres
Publié: (2025)

Enhancing In-Context Learning via Implicit Demonstration Augmentation
par: Zhou, Xiaoling, et autres
Publié: (2024)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
par: Yu, Zhuohao, et autres
Publié: (2025)

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
par: Wang, Yiding, et autres
Publié: (2025)

Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
par: Jia, Hongrui, et autres
Publié: (2025)

Chosen Plaintext Attack on Single Pixel Imaging Encryption via Neural Differential Cryptanalysis
par: Hongran Zeng, et autres
Publié: (2024)

Iron‐Based Sulfate for Sodium‐Ion Batteries: Past, Present, and Future
par: Zhaolu Liu, et autres
Publié: (2024)

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
par: Li, Zehao, et autres
Publié: (2025)

Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
par: Wang, Hongru, et autres
Publié: (2024)

An Empirical Study of Sample Selection Strategies for Large Language Model Repair
par: Li, Xuran, et autres
Publié: (2025)

OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration
par: Guo, Qi, et autres
Publié: (2026)

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling
par: Sun, Hao, et autres
Publié: (2025)

SteerRM: Debiasing Reward Models via Sparse Autoencoders
par: Sun, Mengyuan, et autres
Publié: (2026)

MVSS: A Unified Framework for Multi-View Structured Survey Generation
par: Liu, Yinqi, et autres
Publié: (2026)

DVD: A Robust Method for Detecting Variant Contamination in Large Language Model Evaluation
par: Liang, Renzhao, et autres
Publié: (2026)

Instruction Data Selection via Answer Divergence
par: Li, Bo, et autres
Publié: (2026)