English
Related papers

Related papers: Hard Examples Are All You Need: Maximizing GRPO Po…

200 papers

Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update for those failures without changing rollout generation: it derives a…

Artificial Intelligence · Computer Science 2026-05-14 Duc Anh Le , Tien-Phat Nguyen , Thien Huu Nguyen , Linh Ngo Van , Trung Le

Expensive multi-objective optimization is a prevalent and crucial concern in many real-world scenarios, where sample-efficiency is vital due to the limited evaluations to recover the true Pareto front for decision making. Existing works…

Machine Learning · Computer Science 2026-02-03 Yiming Yao , Fei Liu , Liang Zhao , Xi Lin , Yilu Liu , Qingfu Zhang

Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings. However, the extent to which this extrapolation relies on robust reasoning is unclear. In…

Computation and Language · Computer Science 2023-03-17 Yasaman Razeghi , Robert L. Logan , Matt Gardner , Sameer Singh

As model finetuning is central to the modern NLP, we set to maximize its efficiency. Motivated by redundancy in training examples and the sheer sizes of pretrained models, we exploit a key opportunity: training only on important data. To…

Computation and Language · Computer Science 2023-05-22 Xu Ouyang , Shahina Mohd Azam Ansari , Felix Xiaozhu Lin , Yangfeng Ji

Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. To address this limitation, we propose an active learning…

Machine Learning · Computer Science 2025-04-16 Keyu Duan , Zichen Liu , Xin Mao , Tianyu Pang , Changyu Chen , Qiguang Chen , Michael Qizhe Shieh , Longxu Dou

Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, which are rewarded, and the policy is updated towards the relatively high reward…

Machine Learning · Computer Science 2026-05-22 Nikolay Blagoev , Oğuzhan Ersoy , Wendelin Boehmer , Lydia Yiyu Chen

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Haoxu Wang , Biao Tian , Yiheng Jiang , Zexu Pan , Shengkui Zhao , Bin Ma , Daren Chen , Xiangang Li

When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples to tune a specialised smaller model. In this work, we…

Computation and Language · Computer Science 2026-01-26 Branislav Pecher , Ivan Srba , Maria Bielikova

Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of samples can be annotated. These algorithms often work by…

Computation and Language · Computer Science 2026-04-13 Lorenzo Jaime Yu Flores , Cesare Spinoso di-Piano , Ori Ernst , David Ifeoluwa Adelani , Jackie Chi Kit Cheung

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

Computation and Language · Computer Science 2025-04-15 Nikita Sorokin , Ivan Sedykh , Valentin Malykh

Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present a clear trade-off:…

Computation and Language · Computer Science 2026-02-03 Batuhan K. Karaman , Aditya Rawal , Suhaila Shakiah , Mohammad Ghavamzadeh , Mingyi Hong , Arijit Biswas , Ruida Zhou

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Computation and Language · Computer Science 2020-02-19 Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , Noah Smith

Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Nevertheless, recent studies have revealed that adversarially…

Machine Learning · Computer Science 2023-08-04 Chenhao Lin , Xiang Ji , Yulong Yang , Qian Li , Chao Shen , Run Wang , Liming Fang

Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common corruptions also introduce a large computational overhead,…

Machine Learning · Computer Science 2021-12-07 Weizhe Hua , Yichi Zhang , Chuan Guo , Zhiru Zhang , G. Edward Suh

Beyond maximum likelihood estimation (MLE), the standard objective of a language model (LM) that optimizes good examples probabilities, many studies have explored ways that also penalize bad examples for enhancing the quality of output…

Computation and Language · Computer Science 2024-08-30 Yi-Lin Tuan , William Yang Wang

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to…

Computation and Language · Computer Science 2026-01-05 Brian Yu , Hansen Lillemark , Kurt Keutzer

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Machine Learning · Computer Science 2026-03-06 Ruiqi Zhang , Daman Arora , Song Mei , Andrea Zanette

Recent research demonstrated that training large language models involves memorization of a significant fraction of training data. Such memorization can lead to privacy violations when training on sensitive user data and thus motivates the…

Machine Learning · Computer Science 2025-10-29 Vitaly Feldman , Guy Kornowski , Xin Lyu

Improving model generalization on held-out data is one of the core objectives in commonsense reasoning. Recent work has shown that models trained on the dataset with superficial cues tend to perform well on the easy test set with…

Computation and Language · Computer Science 2021-04-26 Pride Kavumba , Benjamin Heinzerling , Ana Brassard , Kentaro Inui

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

‹ Prev 1 3 4 5 6 7 10 Next ›