English
Related papers

Related papers: Alignment-Aware Decoding

200 papers

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

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

Machine Learning · Computer Science 2026-02-11 Qingnan Ren , Shiting Huang , Zhen Fang , Zehui Chen , Lin Chen , Lijun Li , Feng Zhao

Diffusion models have achieved remarkable progress in text-to-image generation, yet aligning them with human preference remains challenging due to the presence of multiple, sometimes conflicting, evaluation metrics (e.g., semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Dipesh Tamboli , Souradip Chakraborty , Aditya Malusare , Biplab Banerjee , Amrit Singh Bedi , Vaneet Aggarwal

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on…

Computation and Language · Computer Science 2025-05-26 Xuan Qi , Jiahao Qiu , Xinzhe Juan , Yue Wu , Mengdi Wang

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Computation and Language · Computer Science 2025-06-13 Hee Suk Yoon , Eunseop Yoon , Mark Hasegawa-Johnson , Sungwoong Kim , Chang D. Yoo

Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what should stay stable versus what should adapt, rely on static…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Mengzhu Xu , Hanzhi Liu , Ningkang Peng , Qianyu Chen , Canran Xiao

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Amirabbas Afzali , Borna Khodabandeh , Ali Rasekh , Mahyar JafariNodeh , Sepehr kazemi , Simon Gottschalk

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy…

Computation and Language · Computer Science 2026-05-26 Guochao Jiang , Jingyi Song , Guofeng Quan , Chuzhan Hao , Guohua Liu , Yuewei Zhang

This position paper describes and critiques the Pretraining-Agnostic Identically Distributed (PAID) evaluation paradigm, which has become a central tool for measuring progress in natural language understanding. This paradigm consists of…

Computation and Language · Computer Science 2020-05-05 Tal Linzen

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Machine Learning · Computer Science 2024-10-14 Xingzhou Lou , Junge Zhang , Jian Xie , Lifeng Liu , Dong Yan , Kaiqi Huang

Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Fei Wang , Wenxuan Zhou , James Y. Huang , Nan Xu , Sheng Zhang , Hoifung Poon , Muhao Chen

This paper presents Automatic Algorithm Discoverer (AAD), an evolutionary framework for synthesizing programs of high complexity. To guide evolution, prior evolutionary algorithms have depended on fitness (objective) functions, which are…

Neural and Evolutionary Computing · Computer Science 2019-04-08 Ruchira Sasanka , Konstantinos Krommydas

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Computation and Language · Computer Science 2024-11-15 Somanshu Singla , Zhen Wang , Tianyang Liu , Abdullah Ashfaq , Zhiting Hu , Eric P. Xing

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD…

Machine Learning · Computer Science 2021-03-16 Deniz Oktay , Nick McGreivy , Joshua Aduol , Alex Beatson , Ryan P. Adams

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Machine Learning · Computer Science 2025-02-05 Jie Ren , Yuhang Zhang , Dongrui Liu , Xiaopeng Zhang , Qi Tian

Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates…

Machine Learning · Computer Science 2026-05-21 Jungsoo Park , Hyungjoo Chae , Ethan Mendes , Jay DeYoung , Varsha Kishore , Wei Xu , Alan Ritter

Terminology correctness is important in the downstream application of machine translation, and a prevalent way to ensure this is to inject terminology constraints into a translation system. In our submission to the WMT 2023 terminology…

Computation and Language · Computer Science 2023-10-10 Nikolay Bogoychev , Pinzhen Chen

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated,…

Computation and Language · Computer Science 2024-06-07 Afra Amini , Tim Vieira , Ryan Cotterell

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study,…

Computation and Language · Computer Science 2025-10-09 Wafaa Mohammed , Vlad Niculae , Chrysoula Zerva