Cover Image

RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhichao, Wong, Andy, Belkin, Ruslan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

RLSR: Reinforcement Learning from Self Reward
by: Simonds, Toby, et al.
Published: (2025)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
by: Limozin, Alexis, et al.
Published: (2026)

UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function
by: Wang, Zhichao, et al.
Published: (2024)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2026)

SEIF: Self-Evolving Reinforcement Learning for Instruction Following
by: Ren, Qingyu, et al.
Published: (2026)

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
by: Peng, Hao, et al.
Published: (2025)

SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
by: Chen, Yijie, et al.
Published: (2026)

Compositional Instruction Following with Language Models and Reinforcement Learning
by: Cohen, Vanya, et al.
Published: (2025)

Continual SFT Matches Multimodal RLHF with Negative Supervision
by: Zhu, Ke, et al.
Published: (2024)

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
by: Ren, Qingyu, et al.
Published: (2025)

Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability
by: Jia, Jinghan, et al.
Published: (2025)

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
by: He, Yun, et al.
Published: (2025)

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
by: Wang, Bo, et al.
Published: (2025)

Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards
by: Wang, Zhen, et al.
Published: (2025)

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
by: Li, Gang, et al.
Published: (2025)

Learning to Adapt SFT Data for Better Reasoning Generalization
by: Sun, Lisong, et al.
Published: (2026)

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
by: Hong, Joey, et al.
Published: (2024)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
by: Chen, Liang, et al.
Published: (2025)

RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
by: Du, Yuhao, et al.
Published: (2025)

DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
by: Shin, Haebin, et al.
Published: (2025)

LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward
by: Zhao, Yi, et al.
Published: (2025)

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision
by: Gopal, Shreyas, et al.
Published: (2026)

Agentic Reinforcement Learning with Implicit Step Rewards
by: Liu, Xiaoqian, et al.
Published: (2025)

SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
by: Yi, Seungjun, et al.
Published: (2025)

Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
by: Zhang, Kongcheng, et al.
Published: (2025)

Instruction Following without Instruction Tuning
by: Hewitt, John, et al.
Published: (2024)

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
by: Volovikova, Zoya, et al.
Published: (2026)

An Incomplete Loop: Instruction Inference, Instruction Following, and In-context Learning in Language Models
by: Liu, Emmy, et al.
Published: (2024)

CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare
by: Zhu, Jingwei, et al.
Published: (2024)

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
by: Hu, Ziyou, et al.
Published: (2025)

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
by: Xu, Tianze, et al.
Published: (2026)

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
by: Deb, Rohan, et al.
Published: (2025)

Generalizing Verifiable Instruction Following
by: Pyatkin, Valentina, et al.
Published: (2025)

Following Length Constraints in Instructions
by: Yuan, Weizhe, et al.
Published: (2024)

Instruction-Following Pruning for Large Language Models
by: Hou, Bairu, et al.
Published: (2025)

RewardAnything: Generalizable Principle-Following Reward Models
by: Yu, Zhuohao, et al.
Published: (2025)

Instruction Following by Principled Boosting Attention of Large Language Models
by: Guardieiro, Vitoria, et al.
Published: (2025)

Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
by: Zhang, Zhicheng, et al.
Published: (2025)

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