English
Related papers

Related papers: Self-Hinting Language Models Enhance Reinforcement…

200 papers

Recent advances in large language models (LLMs) highlight the importance of post training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimization (GRPO) has shown promise in this domain by combining…

Machine Learning · Computer Science 2026-03-20 Gabriele Carrino , Andrea Sassella , Nicolo Brunello , Federico Toschi , Mark James Carman

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for…

Machine Learning · Computer Science 2026-04-21 Junzhe Wang , Zhiheng Xi , Yajie Yang , Hao Luo , Shihan Dou , Tao Gui , Qi Zhang

This paper investigates whether reward matching is a viable alternative to reward maximization methods for on-policy RL of LLMs. Group-relative Implicit Fine-Tuning (GIFT) is proposed, combining GRPO-style group sampling, DPO-style implicit…

Machine Learning · Computer Science 2026-05-15 Zhichao Wang

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Computation and Language · Computer Science 2025-11-03 Fenia Christopoulou , Ronald Cardenas , Gerasimos Lampouras , Haitham Bou-Ammar , Jun Wang

Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme…

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from…

Machine Learning · Computer Science 2026-03-19 Ziyan Wang , Zheng Wang , Xingwei Qu , Qi Cheng , Jie Fu , Shengpu Tang , Minjia Zhang , Xiaoming Huo

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and…

Machine Learning · Computer Science 2025-12-12 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino , Paolo Mori

Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO for the flow matching-based image generation neglect a…

Machine Learning · Computer Science 2025-12-16 Yawen Shao , Jie Xiao , Kai Zhu , Yu Liu , Wei Zhai , Yang Cao , Zheng-Jun Zha

Group Relative Policy Optimization (GRPO) has significantly advanced the training of large language models and enhanced their reasoning capabilities, while it remains susceptible to instability due to the use of hard clipping. Soft Adaptive…

Machine Learning · Computer Science 2026-03-26 Egor Denisov , Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Alexander Gambashidze , Li Pengyi , Matvey Skripkin , Andrey Galichin , Anton Gusarov , Konstantin Sobolev , Andrey Kuznetsov , Ivan Oseledets

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long…

Artificial Intelligence · Computer Science 2026-03-03 Gang Li , Yan Chen , Ming Lin , Tianbao Yang

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

Recent advances in Large Language Models (LLMs) have transformed text-to-speech (TTS) synthesis, inspiring autoregressive frameworks that represent speech as sequences of discrete codec tokens. Among them, single-codebook TTS LLMs have…

Sound · Computer Science 2025-11-27 Yicheng Zhong , Peiji Yang , Zhisheng Wang

Group Relative Policy Optimization (GRPO) has recently emerged as an effective approach for improving the reasoning capabilities of large language models through online multi-objective reinforcement learning. While personalization on…

Machine Learning · Computer Science 2026-02-03 Ziyao Wang , Daeun Jung , Yexiao He , Guoheng Sun , Zheyu Shen , Myungjin Lee , Ang Li

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Computation and Language · Computer Science 2025-10-13 Shi-Qi Yan , Quan Liu , Zhen-Hua Ling

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

Group Relative Policy Optimization (GRPO) enables stable and preference-oriented updates via group-wise comparisons for post-training video generation. However, GRPO directly optimizes reward-induced advantages. Under sustained…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Rui Li , Yuanzhi Liang , Ziqi Ni , Haibing Huang , Chi Zhang , Xuelong Li

Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…

Machine Learning · Computer Science 2026-02-03 Anthony Zhan