English
Related papers

Related papers: Soft Best-of-n Sampling for Model Alignment

200 papers

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Machine Learning · Computer Science 2025-04-24 Ryan Koo , Ian Yang , Vipul Raheja , Mingyi Hong , Kwang-Sung Jun , Dongyeop Kang

We study best-of-$N$ for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit $N \to \infty$, which we denote as \boinflower. While this approach achieves impressive performance…

Machine Learning · Statistics 2026-03-05 Junpei Komiyama , Daisuke Oba , Masafumi Oyamada

Accurate noise modelling is important for training of deep learning reconstruction algorithms. While noise models are well known for traditional imaging techniques, the noise distribution of a novel sensor may be difficult to determine a…

Machine Learning · Computer Science 2018-07-11 Felix Horger , Tobias Würfl , Vincent Christlein , Andreas Maier

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…

Computation and Language · Computer Science 2022-03-18 Tu Vu , Brian Lester , Noah Constant , Rami Al-Rfou , Daniel Cer

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate this issue, various modifications to a model's sampling…

Computation and Language · Computer Science 2024-01-08 Clara Meister , Tiago Pimentel , Luca Malagutti , Ethan G. Wilcox , Ryan Cotterell

A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this…

Computation and Language · Computer Science 2024-07-22 Zihao Wang , Chirag Nagpal , Jonathan Berant , Jacob Eisenstein , Alex D'Amour , Sanmi Koyejo , Victor Veitch

Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward models are used to approximately model human preferences.…

Machine Learning · Computer Science 2024-03-12 Thomas Coste , Usman Anwar , Robert Kirk , David Krueger

Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large language models. However, it faces a fundamental compute and memory asymmetry: rollout generation is…

Machine Learning · Computer Science 2026-04-23 Yixuan Even Xu , Yash Savani , Fei Fang , J. Zico Kolter

Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming…

Software Engineering · Computer Science 2023-12-29 Yuqi Zhu , Jia Li , Ge Li , YunFei Zhao , Jia Li , Zhi Jin , Hong Mei

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xuexiang Niu , Jinping Tang , Lei Wang , Ge Zhu

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

Machine Learning · Computer Science 2021-06-15 Dara Bahri , Heinrich Jiang

Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a…

Computation and Language · Computer Science 2024-05-17 Guangmin Zheng , Jin Wang , Xiaobing Zhou , Xuejie Zhang

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

Machine Learning · Computer Science 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

Computation and Language · Computer Science 2026-02-23 Raymond Li , Amirhossein Abaskohi , Chuyuan Li , Gabriel Murray , Giuseppe Carenini

Large language models (LLMs) are typically pretrained with next-word prediction (NWP), which yields strong surface fluency but places limited pressure on models to form explicit reasoning before emitting tokens. We study whether shifting…

Computation and Language · Computer Science 2025-09-30 Ming Shen , Zhikun Xu , Jacob Dineen , Xiao Ye , Ben Zhou

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

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Computation and Language · Computer Science 2025-02-28 Yudi Zhang , Lu Wang , Meng Fang , Yali Du , Chenghua Huang , Jun Wang , Qingwei Lin , Mykola Pechenizkiy , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Bingchen Liu , Yizhe Zhu , Zuohui Fu , Gerard de Melo , Ahmed Elgammal

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p (nucleus sampling) often struggle to balance quality and…

Computation and Language · Computer Science 2025-11-21 Minh Nhat Nguyen , Andrew Baker , Clement Neo , Allen Roush , Andreas Kirsch , Ravid Shwartz-Ziv
‹ Prev 1 3 4 5 6 7 10 Next ›