English
Related papers

Related papers: Select Smarter, Not More: Prompt-Aware Evaluation …

200 papers

Cross-topic automated essay scoring (AES) aims to develop a transferable model capable of effectively evaluating essays on a target topic. A significant challenge in this domain arises from the inherent discrepancies between topics. While…

Computation and Language · Computer Science 2025-08-11 Chunyun Zhang , Hongyan Zhao , Chaoran Cui , Qilong Song , Zhiqing Lu , Shuai Gong , Kailin Liu

Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. However, such formulations often misalign with the natural…

Artificial Intelligence · Computer Science 2026-05-08 Lei Gao , Zhuoming Li , Mengxi Jia , Jiakang Yuan , Hongbo Sun , Hao Sun , Xuelong Li

When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum horizon, spending compute on tokens that never receive positive…

Machine Learning · Computer Science 2026-05-29 Zihang Li , Rui Zhou , Yingcheng Shi , Wenhan Yu , Zhewen Tan , Zixiang Liu , Zeming Li , Binhua Li , Yongbin Li , Tong Yang , Jieping Ye

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and parameterizes policies with either continuous Gaussian…

Machine Learning · Computer Science 2020-09-24 Chloe Ching-Yun Hsu , Celestine Mendler-Dünner , Moritz Hardt

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng

Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, demonstrating effectiveness primarily in text-only input…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Qipeng Zhu , Yanzhe Chen , Huasong Zhong , Yan Li , Jie Chen , Zhixin Zhang , Junping Zhang , Zhenheng Yang

Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Haoyang Li , Siyu Zhou , Liang Wang , Guodong Long

High-Performance Computing (HPC) schedulers must balance user performance with facility-wide resource constraints. The task boils down to selecting the optimal number of nodes for a given job. We present a surrogate-assisted multi-objective…

Machine Learning · Computer Science 2026-01-23 Ashna Nawar Ahmed , Banooqa Banday , Terry Jones , Tanzima Z. Islam

Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Xinbo Wang , Shian Jia , Ziyang Huang , Jing Cao , Mingli Song

Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally critical in prompt engineering, where designing effective…

Artificial Intelligence · Computer Science 2026-01-07 Dongyu Chen , Jian Ma , Xianpeng Zhang , Lei Zhang , Haonan Lu , Chen Chen , Chuangchuang Wang , Kai Tang

Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing…

Artificial Intelligence · Computer Science 2025-11-26 Ke Chen , Yifeng Wang , Hassan Almosapeeh , Haohan Wang

The performance of Large Language Models (LLMs) depends heavily on the chosen prompting strategy, yet static approaches such as Zero-Shot, Few-Shot, or Chain-of-Thought (CoT) impose a rigid efficiency-accuracy trade-off. Highly accurate…

Machine Learning · Computer Science 2025-10-01 Jiexi Xu

Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…

Human-Computer Interaction · Computer Science 2026-02-16 Zhipeng Li , Yi-Chi Liao , Christian Holz

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

Computation and Language · Computer Science 2025-07-30 Anas Mohamed , Azal Ahmad Khan , Xinran Wang , Ahmad Faraz Khan , Shuwen Ge , Saman Bahzad Khan , Ayaan Ahmad , Ali Anwar

Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision process which leads to the selected configuration, reduces…

Machine Learning · Computer Science 2023-02-14 Julia Moosbauer , Giuseppe Casalicchio , Marius Lindauer , Bernd Bischl

A growing number of service providers are exploring methods to improve server utilization and reduce power consumption by co-scheduling high-priority latency-critical workloads with best-effort workloads. This practice requires strict…

Machine Learning · Computer Science 2023-03-28 Drew Penney , Bin Li , Jaroslaw Sydir , Lizhong Chen , Charlie Tai , Stefan Lee , Eoin Walsh , Thomas Long

Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2)…

Computation and Language · Computer Science 2026-03-09 Minh Hoang Nguyen , Vu Hoang Pham , Xuan Thanh Huynh , Phuc Hong Mai , Vinh The Nguyen , Quang Nhut Huynh , Huy Tien Nguyen , Tung Le

Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their…

Computation and Language · Computer Science 2024-06-11 MohammadAli SadraeiJavaeri , Ehsaneddin Asgari , Alice Carolyn McHardy , Hamid Reza Rabiee

Subset selection with cost constraints aims to select a subset from a ground set to maximize a monotone objective function without exceeding a given budget, which has various applications such as influence maximization and maximum coverage.…

Data Structures and Algorithms · Computer Science 2024-09-10 Dan-Xuan Liu , Chao Qian