English
Related papers

Related papers: Dynamic Sampling that Adapts: Self-Aware Iterative…

200 papers

Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy…

Artificial Intelligence · Computer Science 2025-08-15 Xingyu Wu , Yuchen Yan , Shangke Lyu , Linjuan Wu , Yiwen Qiu , Yongliang Shen , Weiming Lu , Jian Shao , Jun Xiao , Yueting Zhuang

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

Computation and Language · Computer Science 2025-04-30 Kian Ahrabian , Xihui Lin , Barun Patra , Vishrav Chaudhary , Alon Benhaim , Jay Pujara , Xia Song

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

Computation and Language · Computer Science 2025-06-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…

Computation and Language · Computer Science 2024-10-08 Dahyun Kim , Yungi Kim , Wonho Song , Hyeonwoo Kim , Yunsu Kim , Sanghoon Kim , Chanjun Park

Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter…

Artificial Intelligence · Computer Science 2024-10-15 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Direct Preference Optimization (DPO) is an effective approach for aligning protein language models with experimental design goals. However, DPO faces a scalability bottleneck: the number of possible training pairs grows quadratically with…

Machine Learning · Computer Science 2025-11-27 Constance Ferragu , Jonathan D. Ziegler , Nicolas Deutschmann , Arthur Lindoulsi , Eli Bixby , Cradle ML Team

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Machine Learning · Computer Science 2025-10-07 Yoonjeon Kim , Doohyuk Jang , Eunho Yang

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…

Machine Learning · Computer Science 2026-01-22 Yuhui Sun , Xiyao Wang , Zixi Li , YiTian Ding , Tianyang Ling , Jialuo Chen , Tianyi Yu , Zhenlong Yuan , Jinman Zhao

Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depends on the selection of training data. Recent advances…

Machine Learning · Computer Science 2026-03-12 Yixiu Mao , Yun Qu , Qi Wang , Heming Zou , Xiangyang Ji

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct…

Computation and Language · Computer Science 2025-07-08 Archiki Prasad , Weizhe Yuan , Richard Yuanzhe Pang , Jing Xu , Maryam Fazel-Zarandi , Mohit Bansal , Sainbayar Sukhbaatar , Jason Weston , Jane Yu

Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human…

Artificial Intelligence · Computer Science 2025-05-06 Sarvesh Shashidhar , Ritik , Nachiketa Patil , Suraj Racha , Ganesh Ramakrishnan

Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in…

Computation and Language · Computer Science 2026-02-03 Kaiyuan Chen , Guangmin Zheng , Jin Wang , Xiaobing Zhou , Xuejie Zhang

In various scenarios, a single phase of modelling and solving is either not sufficient or not feasible to solve the problem at hand. A standard approach to solving AI planning problems, for example, is to incrementally extend the planning…

Artificial Intelligence · Computer Science 2020-09-24 Gökberk Koçak , Özgür Akgün , Nguyen Dang , Ian Miguel

Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present a clear trade-off:…

Computation and Language · Computer Science 2026-02-03 Batuhan K. Karaman , Aditya Rawal , Suhaila Shakiah , Mohammad Ghavamzadeh , Mingyi Hong , Arijit Biswas , Ruida Zhou

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

Artificial Intelligence · Computer Science 2024-06-11 Biqing Qi , Pengfei Li , Fangyuan Li , Junqi Gao , Kaiyan Zhang , Bowen Zhou

Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Best-of-N sampling ($N\geq8$) to mine positive trajectories…

Computation and Language · Computer Science 2026-05-29 Jun Rao , Zixiong Yu , Xuebo Liu , Guhan Chen , Jing Li , Hejin Wang , Jiansheng Wei , Xiaojun Meng , Min Zhang

DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have…

Computation and Language · Computer Science 2025-08-26 Chenxu Yang , Ruipeng Jia , Naibin Gu , Zheng Lin , Siyuan Chen , Chao Pang , Weichong Yin , Yu Sun , Hua Wu , Weiping Wang

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Software Engineering · Computer Science 2025-12-09 Xin Yin , Chao Ni , Xiaohu Yang