English
Related papers

Related papers: Differentiable lower bound for expected BLEU score

200 papers

The natural language understanding (NLU) performance of large language models (LLMs) has been evaluated across various tasks and datasets. The existing evaluation methods, however, do not take into account the variance in scores due to…

Computation and Language · Computer Science 2024-08-23 Yusuke Sakai , Adam Nohejl , Jiangnan Hang , Hidetaka Kamigaito , Taro Watanabe

We present a reinforcement learning (RL) approach for robust optimisation of risk-aware performance criteria. To allow agents to express a wide variety of risk-reward profiles, we assess the value of a policy using rank dependent expected…

Machine Learning · Computer Science 2021-12-16 Sebastian Jaimungal , Silvana Pesenti , Ye Sheng Wang , Hariom Tatsat

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Computation and Language · Computer Science 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined…

Optimization and Control · Mathematics 2024-01-02 Dongsheng Ding , Zhengyan Huan , Alejandro Ribeiro

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they…

Software Engineering · Computer Science 2020-09-29 Shuo Ren , Daya Guo , Shuai Lu , Long Zhou , Shujie Liu , Duyu Tang , Neel Sundaresan , Ming Zhou , Ambrosio Blanco , Shuai Ma

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a…

Machine Learning · Computer Science 2026-05-20 Jaemoo Choi , Yuchen Zhu , Wei Guo , Petr Molodyk , Bo Yuan , Jinbin Bai , Yi Xin , Molei Tao , Yongxin Chen

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Machine Learning · Computer Science 2025-12-04 Chujie Zheng , Kai Dang , Bowen Yu , Mingze Li , Huiqiang Jiang , Junrong Lin , Yuqiong Liu , Hao Lin , Chencan Wu , Feng Hu , An Yang , Jingren Zhou , Junyang Lin

The Bayesian Cram\'er-Rao bound (CRB) provides a lower bound on the mean square error of any Bayesian estimator under mild regularity conditions. It can be used to benchmark the performance of statistical estimators, and provides a…

Machine Learning · Statistics 2024-09-09 Evan Scope Crafts , Xianyang Zhang , Bo Zhao

Sparse linear discriminant analysis via penalized optimal scoring is a successful tool for classification in high-dimensional settings. While the variable selection consistency of sparse optimal scoring has been established, the…

Statistics Theory · Mathematics 2021-04-01 Irina Gaynanova

Debiased recommendation with a randomized dataset has shown very promising results in mitigating the system-induced biases. However, it still lacks more theoretical insights or an ideal optimization objective function compared with the…

Information Retrieval · Computer Science 2023-03-22 Dugang Liu , Pengxiang Cheng , Zinan Lin , Xiaolian Zhang , Zhenhua Dong , Rui Zhang , Xiuqiang He , Weike Pan , Zhong Ming

This paper presents a new static analysis for deriving upper bounds on the expected resource consumption of probabilistic programs. The analysis is fully automatic and derives symbolic bounds that are multivariate polynomials of the inputs.…

Programming Languages · Computer Science 2017-11-27 Van Chan Ngo , Quentin Carbonneaux , Jan Hoffmann

The assessment of binary classifier performance traditionally centers on discriminative ability using metrics, such as accuracy. However, these metrics often disregard the model's inherent uncertainty, especially when dealing with sensitive…

Machine Learning · Computer Science 2024-02-13 Agathe Fernandes Machado , Arthur Charpentier , Emmanuel Flachaire , Ewen Gallic , François Hu

We study the fundamental problem of ReLU regression, where the goal is to fit Rectified Linear Units (ReLUs) to data. This supervised learning task is efficiently solvable in the realizable setting, but is known to be computationally hard…

Machine Learning · Computer Science 2022-01-27 Ilias Diakonikolas , Jongho Park , Christos Tzamos

Cloze testing is a common method for measuring the behavior of large language models on a number of benchmark tasks. Using the MMLU dataset, we show that the base-rate probability (BRP) differences across answer tokens are significant and…

Computation and Language · Computer Science 2024-10-01 Kyle Moore , Jesse Roberts , Thao Pham , Oseremhen Ewaleifoh , Doug Fisher

This paper considers the classical problem of sampling with Monte Carlo methods a target rare event distribution defined by a score function that is very expensive to compute. We assume we can build using evaluations of the true score, an…

Computation · Statistics 2024-10-25 Frédéric Cérou , Patrick Héas , Mathias Rousset

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Computation and Language · Computer Science 2020-04-02 Yifan Xu , Kening Zhang , Haoyu Dong , Yuezhou Sun , Wenlong Zhao , Zhuowen Tu

Optimization models used to make discrete decisions often contain uncertain parameters that are context-dependent and estimated through prediction. To account for the quality of the decision made based on the prediction, decision-focused…

Machine Learning · Computer Science 2024-07-30 Noah Schutte , Krzysztof Postek , Neil Yorke-Smith

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…

Computation and Language · Computer Science 2025-05-28 Hexuan Deng , Wenxiang Jiao , Xuebo Liu , Jing Li , Min Zhang , Zhaopeng Tu

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine
‹ Prev 1 4 5 6 7 8 10 Next ›