English
Related papers

Related papers: Confidence-Aware Alignment Makes Reasoning LLMs Mo…

200 papers

We present VAPO, Value-based Augmented Proximal Policy Optimization framework for reasoning models., a novel framework tailored for reasoning models within the value-based paradigm. Benchmarked the AIME 2024 dataset, VAPO, built on the Qwen…

Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. One solution is to route intermediate chain-of-thought (CoT)…

Artificial Intelligence · Computer Science 2026-05-08 Wenwen Si , Insup Lee , Osbert Bastani

Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigations have been conducted to understand CoT, the underlying…

Computation and Language · Computer Science 2024-10-23 Yingqian Cui , Pengfei He , Xianfeng Tang , Qi He , Chen Luo , Jiliang Tang , Yue Xing

Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial latency and compute costs. We address a fundamental theoretical question: how many reasoning…

Artificial Intelligence · Computer Science 2026-05-29 Kiran Tomlinson , Tobias Schnabel , Adith Swaminathan , Jennifer Neville

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

Machine Learning · Statistics 2026-02-03 Shokichi Takakura , Akifumi Wachi , Rei Higuchi , Kohei Miyaguchi , Taiji Suzuki

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Cryptography and Security · Computer Science 2026-03-17 Yu Pan , Wenlong Yu , Tiejun Wu , Xiaohu Ye , Qiannan Si , Guangquan Xu , Bin Wu

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length…

Artificial Intelligence · Computer Science 2025-06-03 Yuliang Liu , Junjie Lu , Zhaoling Chen , Chaofeng Qu , Jason Klein Liu , Chonghan Liu , Zefan Cai , Yunhui Xia , Li Zhao , Jiang Bian , Chuheng Zhang , Wei Shen , Zhouhan Lin

As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now…

Computation and Language · Computer Science 2026-01-21 Zhenjiang Mao , Anirudhh Venkat

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Computation and Language · Computer Science 2024-10-14 Yiju Guo , Ganqu Cui , Lifan Yuan , Ning Ding , Zexu Sun , Bowen Sun , Huimin Chen , Ruobing Xie , Jie Zhou , Yankai Lin , Zhiyuan Liu , Maosong Sun

Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for recommendation systems, which usually adapt a pre-trained LLM to the recommendation scenario through supervised fine-tuning (SFT). However, both the…

Information Retrieval · Computer Science 2024-10-17 Jiayi Liao , Xiangnan He , Ruobing Xie , Jiancan Wu , Yancheng Yuan , Xingwu Sun , Zhanhui Kang , Xiang Wang

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data.…

Computation and Language · Computer Science 2026-04-20 Junyi Li , Yongqiang Chen , Ningning Ding

State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at…

Machine Learning · Computer Science 2026-04-21 Muhammed Emrullah Ildiz , Halil Alperen Gozeten , Ege Onur Taga , Samet Oymak

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…

Artificial Intelligence · Computer Science 2026-01-01 Lijun Zhang , Lin Li , Wei Wei , Yajie Qi , Huizhong Song , Jun Wang , Yaodong Yang , Jiye Liang

Mathematical reasoning through Chain-of-Thought (CoT) has emerged as a powerful capability of Large Language Models (LLMs), which can be further enhanced through Test-Time Scaling (TTS) methods like Beam Search and DVTS. However, these…

Computation and Language · Computer Science 2025-05-26 Zezhong Wang , Xingshan Zeng , Weiwen Liu , Yufei Wang , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu , Kam-Fai Wong

Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning and open-world generalization. However, the excessive computational overhead and high…

Robotics · Computer Science 2026-05-26 Ruoyu Yao , Ruiguo Zhong , Pei Liu , Mingxing Peng , Rui Yang , Jun Ma

Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yufei He , Tri Cao , Simeng Han , Yulin Chen , Bryan Hooi

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainly focus on…

Computation and Language · Computer Science 2026-04-20 Yao Chen , Jiawei Sheng , Wenyuan Zhang , Tingwen Liu

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confidence estimation…

Computation and Language · Computer Science 2026-05-20 Xiaoou Liu , Tiejin Chen , Dengjia Zhang , Yaqing Wang , Lu Cheng , Hua Wei

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra