English
Related papers

Related papers: NPO: Learning Alignment and Meta-Alignment through…

200 papers

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised…

Artificial Intelligence · Computer Science 2026-04-20 Jun Rao , Xuebo Liu , Hexuan Deng , Zepeng Lin , Zixiong Yu , Jiansheng Wei , Xiaojun Meng , Min Zhang

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

Computation and Language · Computer Science 2024-06-06 Dehong Xu , Liang Qiu , Minseok Kim , Faisal Ladhak , Jaeyoung Do

Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design.…

Computation and Language · Computer Science 2025-02-27 Wenxin Luo , Weirui Wang , Xiaopeng Li , Weibo Zhou , Pengyue Jia , Xiangyu Zhao

The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still rely heavily on substantial paired (labeled) feedback data,…

Machine Learning · Computer Science 2026-02-20 Seonggyun Lee , Sungjun Lim , Seojin Park , Soeun Cheon , Kyungwoo Song

Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g.,…

Machine Learning · Computer Science 2026-03-09 Xiaocan Li , Shiliang Wu , Zheng Shen

Personalization and contextual coherence are two essential components in building effective persona-grounded dialogue systems. These aspects play a crucial role in enhancing user engagement and ensuring responses are more relevant and…

Computation and Language · Computer Science 2026-02-05 Saleh Afzoon , MohammadHossein Ahmadi , Usman Naseem , Amin Beheshti

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…

Computation and Language · Computer Science 2024-06-27 Shiva Kumar Pentyala , Zhichao Wang , Bin Bi , Kiran Ramnath , Xiang-Bo Mao , Regunathan Radhakrishnan , Sitaram Asur , Na , Cheng

Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function…

Machine Learning · Computer Science 2023-12-25 Alexandre Maraval , Matthieu Zimmer , Antoine Grosnit , Haitham Bou Ammar

Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs and values. We contribute to this pursuit with a dynamic…

Machine Learning · Computer Science 2024-11-01 Hadassah Harland , Richard Dazeley , Peter Vamplew , Hashini Senaratne , Bahareh Nakisa , Francisco Cruz

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where…

Machine Learning · Computer Science 2026-05-20 Ankita Awasthi , Marco Apolinario , Kaushik Roy

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

Machine Learning · Computer Science 2025-09-17 Denis Janiak , Julia Moska , Dawid Motyka , Karolina Seweryn , Paweł Walkowiak , Bartosz Żuk , Arkadiusz Janz

While error backpropagation (BP) has dominated the training of nearly all modern neural networks for a long time, it suffers from several biological plausibility issues such as the symmetric weight requirement and synchronous updates.…

Neurons and Cognition · Quantitative Biology 2023-04-05 Huzi Cheng , Joshua W. Brown

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Machine Learning · Computer Science 2025-10-07 Yoonjeon Kim , Doohyuk Jang , Eunho Yang

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Machine Learning · Computer Science 2025-06-16 Megan Tjandrasuwita , Chanakya Ekbote , Liu Ziyin , Paul Pu Liang

Formal verification provides assurances that a probabilistic system satisfies its specification--conditioned on the system model being aligned with reality. We propose alignment monitoring to watch that this assumption is justified. We…

Logic in Computer Science · Computer Science 2025-08-04 Thomas A. Henzinger , Konstantin Kueffner , Vasu Singh , I Sun

This paper represents a novel online self-learning disturbance observer (SLDO) by benefiting from the combination of a type-2 neuro-fuzzy structure (T2NFS), feedback-error learning scheme and sliding mode control (SMC) theory. The SLDO is…

Systems and Control · Electrical Eng. & Systems 2021-03-30 Erkan Kayacan , Joshua M. Peschel , Girish Chowdhary

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Artificial Intelligence · Computer Science 2026-04-15 Zhicong Li , Lingjie Jiang , Yulan Hu , Xingchen Zeng , Yixia Li , Xiangwen Zhang , Guanhua Chen , Zheng Pan , Xin Li , Yong Liu

In recent years, text-to-speech (TTS) has seen impressive advancements through large-scale language models, achieving human-level speech quality. Integrating human feedback has proven effective for enhancing robustness in these systems.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Kangxiang Xia , Xinfa Zhu , Jixun Yao , Lei Xie