English
Related papers

Related papers: Rethinking Prompt Optimizers: From Prompt Merits t…

200 papers

Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated…

Artificial Intelligence · Computer Science 2025-07-14 Rin Ashizawa , Yoichi Hirose , Nozomu Yoshinari , Kento Uchida , Shinichi Shirakawa

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where…

Computation and Language · Computer Science 2024-10-14 Yurong Wu , Yan Gao , Bin Benjamin Zhu , Zineng Zhou , Xiaodi Sun , Sheng Yang , Jian-Guang Lou , Zhiming Ding , Linjun Yang

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

Artificial Intelligence · Computer Science 2024-10-25 Yibo Miao , Bofei Gao , Shanghaoran Quan , Junyang Lin , Daoguang Zan , Jiaheng Liu , Jian Yang , Tianyu Liu , Zhijie Deng

Optimizing Large Language Model (LLM) performance requires well-crafted prompts, but manual prompt engineering is labor-intensive and often ineffective. Automated prompt optimization techniques address this challenge but the majority of…

Computation and Language · Computer Science 2025-08-20 Ximing Dong , Shaowei Wang , Dayi Lin , Ahmed E. Hassan

Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). While prior work has emphasized algorithmic design, data curation, and reward shaping, we investigate…

Machine Learning · Computer Science 2025-07-10 Xinjie Chen , Minpeng Liao , Guoxin Chen , Chengxi Li , Biao Fu , Kai Fan , Xinggao Liu

Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explicit, recent works…

Computation and Language · Computer Science 2023-04-10 Peifeng Wang , Aaron Chan , Filip Ilievski , Muhao Chen , Xiang Ren

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as…

Artificial Intelligence · Computer Science 2026-01-14 Jinpeng Wang , Chao Li , Ting Ye , Mengyuan Zhang , Wei Liu , Jian Luan

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Computation and Language · Computer Science 2024-12-23 Shuo Xie , Fangzhi Zhu , Jiahui Wang , Lulu Wen , Wei Dai , Xiaowei Chen , Junxiong Zhu , Kai Zhou , Bo Zheng

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

Machine Learning · Computer Science 2025-02-04 Mingze Kong , Zhiyong Wang , Yao Shu , Zhongxiang Dai

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

Designing effective prompts can empower LLMs to understand user preferences and provide recommendations with intent comprehension and knowledge utilization capabilities. Nevertheless, recent studies predominantly concentrate on task-wise…

Information Retrieval · Computer Science 2025-02-04 Wenyu Mao , Jiancan Wu , Weijian Chen , Chongming Gao , Xiang Wang , Xiangnan He

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Computation and Language · Computer Science 2025-05-27 Yeyuan Wang , Dehong Gao , Rujiao Long , Lei Yi , Linbo Jin , Libin Yang , Xiaoyan Cai

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly…

Artificial Intelligence · Computer Science 2024-06-11 Weize Kong , Spurthi Amba Hombaiah , Mingyang Zhang , Qiaozhu Mei , Michael Bendersky

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Hyperparameter optimization (HPO) is important to leverage the full potential of machine learning (ML). In practice, users are often interested in multi-objective (MO) problems, i.e., optimizing potentially conflicting objectives, like…

Machine Learning · Computer Science 2024-01-12 Joseph Giovanelli , Alexander Tornede , Tanja Tornede , Marius Lindauer

While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is…

Machine Learning · Computer Science 2026-05-29 Hyunji Nam , Haoran Li , Natasha Jaques

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

Computation and Language · Computer Science 2024-07-01 Shouchang Guo , Sonam Damani , Keng-hao Chang

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, with their performance heavily dependent on the quality of input prompts. While prompt engineering has proven effective, it typically relies on…

Neural and Evolutionary Computing · Computer Science 2025-04-17 Xavier Sécheresse , Jacques-Yves Guilbert--Ly , Antoine Villedieu de Torcy