English
Related papers

Related papers: Learning to Choose or Choosing to Learn: Best-of-N…

200 papers

Best-of-N (BoN) is a popular and effective algorithm for aligning language models to human preferences. The algorithm works as follows: at inference time, N samples are drawn from the language model, and the sample with the highest reward,…

Computation and Language · Computer Science 2025-03-05 Afra Amini , Tim Vieira , Elliott Ash , Ryan Cotterell

This paper concerns the problem of aligning samples from large language models to human preferences using best-of-$n$ sampling, where we draw $n$ samples, rank them, and return the best one. We consider two fundamental problems. First: what…

Computation and Language · Computer Science 2024-11-05 Lin Gui , Cristina Gârbacea , Victor Veitch

Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the highest predicted reward according to a learned reward…

Machine Learning · Computer Science 2026-03-09 Ved Sriraman , Adam Block

Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitFit and adapter…

Machine Learning · Computer Science 2024-01-09 Nigel Doering , Cyril Gorlla , Trevor Tuttle , Adhvaith Vijay

Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N) candidate is a popular approach to achieve higher accuracy in tasks with discrete final answers.…

Machine Learning · Computer Science 2025-11-25 Amin Rakhsha , Kanika Madan , Tianyu Zhang , Amir-massoud Farahmand , Amir Khasahmadi

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Machine Learning · Computer Science 2026-03-31 Ali Taheri , Alireza Taban , Qizhou Wang , Shanshan Ye , Abdolreza Mirzaei , Tongliang Liu , Bo Han

Best-of-$n$ (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating $n$ responses to a prompt and then selecting the sample…

Information Theory · Computer Science 2025-05-07 Claudio Mayrink Verdun , Alex Oesterling , Himabindu Lakkaraju , Flavio P. Calmon

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

Machine Learning · Computer Science 2023-11-10 Paolo Didier Alfano , Vito Paolo Pastore , Lorenzo Rosasco , Francesca Odone

Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response…

Methodology · Statistics 2025-10-14 Hyung Gyu Rho , Sian Lee

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

Computation and Language · Computer Science 2019-10-09 Alberto Poncelas , Gideon Maillette de Buy Wenniger , Andy Way

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

Computation and Language · Computer Science 2023-08-03 Zhiqiang Yuan , Junwei Liu , Qiancheng Zi , Mingwei Liu , Xin Peng , Yiling Lou

While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation,…

Computation and Language · Computer Science 2019-06-12 Matthew E. Peters , Sebastian Ruder , Noah A. Smith

Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs). In this work, we propose a novel inference-aware fine-tuning paradigm, in which…

Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutions generated by the LLM are ranked by a verifier, and the…

Machine Learning · Computer Science 2025-02-25 Lunjun Zhang , Arian Hosseini , Hritik Bansal , Mehran Kazemi , Aviral Kumar , Rishabh Agarwal

Test-time scaling enhances large language model performance by allocating additional compute resources during inference. Best-of-N (BoN) sampling serves as a common sampling-based scaling technique, broadening the search space in parallel…

Computation and Language · Computer Science 2025-11-04 Yiming Wang , Pei Zhang , Siyuan Huang , Baosong Yang , Zhuosheng Zhang , Fei Huang , Rui Wang

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised…

Computation and Language · Computer Science 2022-10-24 Bohong Wu , Hai Zhao

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…

Computation and Language · Computer Science 2024-07-09 Eric Pasewark , Kyle Montgomery , Kefei Duan , Dawn Song , Chenguang Wang

Attention mechanism is a fundamental component of the transformer model and plays a significant role in its success. However, the theoretical understanding of how attention learns to select tokens is still an emerging area of research. In…

Machine Learning · Computer Science 2025-05-20 Keitaro Sakamoto , Issei Sato

Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…

Computation and Language · Computer Science 2024-02-19 Dheeraj Mekala , Alex Nguyen , Jingbo Shang
‹ Prev 1 2 3 10 Next ›