English
Related papers

Related papers: AdaBoN: Adaptive Best-of-N Alignment

200 papers

Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…

Computation and Language · Computer Science 2024-12-24 Jianpeng Zhou , Wanjun Zhong , Yanlin Wang , Jiahai Wang

Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…

Computation and Language · Computer Science 2026-04-13 Yuyan Zhou , Kai Syun Hou , Weiyu Chen , James Kwok

Aligning large language models (LLMs) to serve users with heterogeneous and potentially conflicting preferences is a central challenge for personalized and trustworthy AI. We formalize an ideal notion of universal alignment through…

Machine Learning · Computer Science 2026-01-14 Yang Cai , Weiqiang Zheng

Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal…

In many real-world applications, it is hard to provide a reward signal in each step of a Reinforcement Learning (RL) process and more natural to give feedback when an episode ends. To this end, we study the recently proposed model of RL…

Machine Learning · Computer Science 2024-05-15 Asaf Cassel , Haipeng Luo , Aviv Rosenberg , Dmitry Sotnikov

Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple and…

Computation and Language · Computer Science 2023-10-20 Reid Pryzant , Dan Iter , Jerry Li , Yin Tat Lee , Chenguang Zhu , Michael Zeng

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive generative LLMs,…

Machine Learning · Computer Science 2025-11-04 David Lüdke , Tom Wollschläger , Paul Ungermann , Stephan Günnemann , Leo Schwinn

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Artificial Intelligence · Computer Science 2025-08-19 Jiayi Pan , Xiuyu Li , Long Lian , Charlie Snell , Yifei Zhou , Adam Yala , Trevor Darrell , Kurt Keutzer , Alane Suhr

While chain-of-thought prompting with Best-of-N (BoN) selection has become popular for mathematical reasoning in large language models (LLMs), its linear structure fails to capture the branching and exploratory nature of complex…

Machine Learning · Computer Science 2025-10-24 Tristan Cinquin , Geoff Pleiss , Agustinus Kristiadi

Token-level Chain-of-Thought (CoT) prompting has become a standard way to elicit multi-step reasoning in large language models (LLMs), especially for mathematical word problems. However, generating long intermediate traces increases output…

Computation and Language · Computer Science 2026-03-17 Disha Sheshanarayana , Rajat Subhra Pal , Manjira Sinha , Tirthankar Dasgupta

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework…

Computation and Language · Computer Science 2024-03-19 Yuhang Lai , Siyuan Wang , Shujun Liu , Xuanjing Huang , Zhongyu Wei

Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent…

Computation and Language · Computer Science 2026-04-27 Pretam Ray , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current…

Computation and Language · Computer Science 2024-11-05 Jiaming Ji , Boyuan Chen , Hantao Lou , Donghai Hong , Borong Zhang , Xuehai Pan , Juntao Dai , Tianyi Qiu , Yaodong Yang

Test-time compute has emerged as a key paradigm for enhancing LLM reasoning, yet prevailing approaches like Best-of-N and majority voting apply uniform depth across inputs, wasting computation on simple queries while potentially…

Artificial Intelligence · Computer Science 2025-09-30 Yixin He , Lumingyuan Tang

Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards. However, most studies apply RL to the full denoising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Renye Yan , Jikang Cheng , Shikun Sun , Yi Sun , You Wu , Wei Peng , Zongwei Wang , Ling Liang , Junliang Xing , Yimao Cai

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hao Li , Hong Zhang , Xiaojuan Qi , Ruigang Yang , Gao Huang

Prompt engineering has proven to be a crucial step in leveraging pretrained large language models (LLMs) in solving various real-world tasks. Numerous solutions have been proposed that seek to automate prompt engineering by using the model…

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang

We propose a novel prompt design paradigm that challenges conventional wisdom in large language model (LLM) prompting. While conventional wisdom prioritizes well-crafted instructions and demonstrations for in-context learning (ICL), we show…

Artificial Intelligence · Computer Science 2025-06-24 Jianyu Wang , Zhiqiang Hu , Lidong Bing

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Computation and Language · Computer Science 2024-12-25 Shuzhang Cai , Twumasi Mensah-Boateng , Xander Kuksov , Jing Yuan , Shaojie Tang
‹ Prev 1 8 9 10 Next ›