English
Related papers

Related papers: Variational Best-of-N Alignment

200 papers

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Machine Learning · Computer Science 2024-07-04 Adam X. Yang , Maxime Robeyns , Thomas Coste , Zhengyan Shi , Jun Wang , Haitham Bou-Ammar , Laurence Aitchison

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Machine Learning · Computer Science 2024-05-13 Seungwook Han , Idan Shenfeld , Akash Srivastava , Yoon Kim , Pulkit Agrawal

Obtaining high-quality generations in modern LLMs has largely been framed as a selection problem: identifying a single winning generation from a diverse pool of N samples, the Best-of-N (BoN). Yet, this approach is inherently zero-sum,…

Computation and Language · Computer Science 2025-10-02 Ammar Khairi , Daniel D'souza , Marzieh Fadaee , Julia Kreutzer

Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-N distillation (BOND). However, the iterative BOND algorithm is prohibitively expensive in practice due to the…

Machine Learning · Computer Science 2025-02-20 Tong Yang , Jincheng Mei , Hanjun Dai , Zixin Wen , Shicong Cen , Dale Schuurmans , Yuejie Chi , Bo Dai

A simple and effective method for the inference-time alignment and scaling test-time compute of generative models is best-of-$n$ sampling, where $n$ samples are drawn from a reference policy, ranked based on a reward function, and the…

Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their…

Machine Learning · Computer Science 2024-10-29 Ruizhe Shi , Yifang Chen , Yushi Hu , Alisa Liu , Hannaneh Hajishirzi , Noah A. Smith , Simon S. Du

Large Language Models have revolutionized recommender systems (LLM4Rec) by leveraging their generative capabilities to model complex user preferences. However, existing LLM4Rec methods primarily rely on token-level objectives, making it…

Information Retrieval · Computer Science 2026-05-07 Ruijun Chen , Chongming Gao , Jiawei Chen , Weiqin Yang , Xiangnan He

Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question of how best to use the additional compute remains open. A popular approach is BoN…

Machine Learning · Computer Science 2026-04-07 Zhuohao Yu , Zhiwei Steven Wu , Adam Block

The application of Reinforcement Learning with Verifiable Rewards (RLVR) to mathematical and coding domains has demonstrated significant improvements in the reasoning and problem-solving abilities of Large Language Models. Despite its…

Machine Learning · Computer Science 2025-10-28 Farid Bagirov , Mikhail Arkhipov , Ksenia Sycheva , Evgeniy Glukhov , Egor Bogomolov

Inference-time alignment effectively steers large language models (LLMs) by generating multiple candidates from a reference model and selecting among them with an imperfect reward model. However, current strategies face a fundamental…

Artificial Intelligence · Computer Science 2026-03-10 Hsiang Hsu , Eric Lei , Chun-Fu Chen

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Computation and Language · Computer Science 2025-12-15 Zhewei Kang , Xuandong Zhao , Dawn Song

Best-of-N (BoN) sampling, a common strategy for test-time scaling of Large Language Models (LLMs), relies on reward models to select the best candidate solution from multiple generations. However, traditional reward models often assign…

Computation and Language · Computer Science 2025-02-20 Yantao Liu , Zijun Yao , Rui Min , Yixin Cao , Lei Hou , Juanzi Li

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 compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of-$n$ (BoN) sampling and sequential revision, their fundamental limits…

Machine Learning · Computer Science 2025-12-05 Yue Yu , Qiwei Di , Quanquan Gu , Dongruo Zhou

Test-time scaling has emerged as a critical avenue for enhancing the reasoning capabilities of Large Language Models (LLMs). Though the straight-forward ''best-of-$N$'' (BoN) strategy has already demonstrated significant improvements in…

Machine Learning · Computer Science 2026-02-03 Muheng Li , Jian Qian , Wenlong Mou

Let $p$ denote a generative language model. Let $r$ denote a reward model that returns a scalar that captures the degree at which a draw from $p$ is preferred. The goal of language model alignment is to alter $p$ to a new distribution…

Machine Learning · Computer Science 2024-04-03 Joy Qiping Yang , Salman Salamatian , Ziteng Sun , Ananda Theertha Suresh , Ahmad Beirami

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen…

Artificial Intelligence · Computer Science 2025-10-31 Guohao Sun , Hang Hua , Jian Wang , Jiebo Luo , Sohail Dianat , Majid Rabbani , Raghuveer Rao , Zhiqiang Tao

Variational inference (VI) provides a principled framework for estimating posterior distributions over model parameters, enabling explicit modeling of weight uncertainty during optimization. By capturing this uncertainty, VI improves the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Haolin Chen

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Machine Learning · Computer Science 2026-02-17 Seongho Son , William Bankes , Sangwoong Yoon , Shyam Sundhar Ramesh , Xiaohang Tang , Ilija Bogunovic

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal…

Computation and Language · Computer Science 2024-02-27 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Anh Tuan Luu