English
Related papers

Related papers: Data Diversification Methods In Alignment Enhance …

200 papers

We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of high-state complexity. From a generated pool of proposals, our…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Sinisa Stekovic , Mahdi Rad , Alireza Moradi , Friedrich Fraundorfer , Vincent Lepetit

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…

Machine Learning · Computer Science 2024-06-28 Xin Lai , Zhuotao Tian , Yukang Chen , Senqiao Yang , Xiangru Peng , Jiaya Jia

Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily…

Machine Learning · Computer Science 2024-06-27 Jikun Kang , Xin Zhe Li , Xi Chen , Amirreza Kazemi , Qianyi Sun , Boxing Chen , Dong Li , Xu He , Quan He , Feng Wen , Jianye Hao , Jun Yao

While Test-Time Scaling (TTS) has proven effective in improving the reasoning ability of large language models (LLMs), low diversity in model outputs often becomes a bottleneck; this is partly caused by the common "one problem, one…

Computation and Language · Computer Science 2026-01-06 Feng Ju , Zeyu Qin , Rui Min , Zhitao He , Lingpeng Kong , Yi R. Fung

The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various proposed data construction methods, their practical utility in…

Computation and Language · Computer Science 2025-10-09 Yike Zhao , Simin Guo , Ziqing Yang , Shifan Han , Dahua Lin , Fei Tan

In math reasoning with large language models (LLMs), fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective, profoundly narrowing the gap between open-sourced LLMs and cutting-edge…

Computation and Language · Computer Science 2024-07-18 Chengpeng Li , Zheng Yuan , Hongyi Yuan , Guanting Dong , Keming Lu , Jiancan Wu , Chuanqi Tan , Xiang Wang , Chang Zhou

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair…

Computation and Language · Computer Science 2026-04-13 Chia-Hsuan Lee , Mingyang Zhou , Renkun Ni , Zelei Cheng , Sihui Dai , Supriyo Chakraborty , Shixiong Zhang , Sambit Sahu , William Campbell

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling…

Computation and Language · Computer Science 2025-03-07 Jinlong Pang , Jiaheng Wei , Ankit Parag Shah , Zhaowei Zhu , Yaxuan Wang , Chen Qian , Yang Liu , Yujia Bao , Wei Wei

Requiring a large language model (LLM) to generate intermediary reasoning steps, known as Chain of Thought (CoT), has been shown to be an effective way of boosting performance. Previous approaches have focused on generating multiple…

Computation and Language · Computer Science 2025-05-28 Haritz Puerto , Tilek Chubakov , Xiaodan Zhu , Harish Tayyar Madabushi , Iryna Gurevych

Large Language Models (LLMs) have demonstrated strong reasoning capabilities in solving complex problems. However, current approaches primarily enhance reasoning through the elaboration of thoughts while neglecting the diversity of…

Computation and Language · Computer Science 2025-04-25 Danqing Wang , Jianxin Ma , Fei Fang , Lei Li

Large Language Models (LLMs) have exhibited remarkable capabilities in many complex tasks including mathematical reasoning. However, traditional approaches heavily rely on ensuring self-consistency within single prompting method, which…

Computation and Language · Computer Science 2024-10-15 Gisang Lee , Sangwoo Park , Junyoung Park , Andrew Chung , Sieun Park , Yoonah Park , Byungju Kim , Min-gyu Cho

Large language models (LLMs) have demonstrated impressive task-solving capabilities through prompting techniques and system designs, including solving planning tasks (e.g., math proofs, basic travel planning) when sufficient data is…

Artificial Intelligence · Computer Science 2025-04-25 Wenjun Li , Changyu Chen , Pradeep Varakantham

Large language models (LLMs) have made impressive progress in handling simple math problems, yet they still struggle with more challenging and complex mathematical tasks. In this paper, we introduce a series of LLMs that employs the…

Computation and Language · Computer Science 2024-07-18 Chengpeng Li , Guanting Dong , Mingfeng Xue , Ru Peng , Xiang Wang , Dayiheng Liu

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Computation and Language · Computer Science 2023-08-24 Kushal Tirumala , Daniel Simig , Armen Aghajanyan , Ari S. Morcos

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…

Machine Learning · Computer Science 2025-12-02 Kuangpu Guo , Yuhe Ding , Jian Liang , Zilei Wang , Ran He

Preference optimization methods have been successfully applied to improve not only the alignment of large language models (LLMs) with human values, but also specific natural language tasks such as summarization and stylistic continuations.…

Machine Learning · Computer Science 2025-02-06 Salem Lahlou , Abdalgader Abubaker , Hakim Hacid

LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high benchmarks scores on SWE-bench, their API dependence, cost, and…

Software Engineering · Computer Science 2025-06-17 Yibo Wang , Zhihao Peng , Ying Wang , Zhao Wei , Hai Yu , Zhiliang Zhu

Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements…

Machine Learning · Computer Science 2025-07-15 Hoang Anh Just , Mahavir Dabas , Lifu Huang , Ming Jin , Ruoxi Jia

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the significance…

Computation and Language · Computer Science 2024-03-05 Bingshuai Liu , Chenyang Lyu , Zijun Min , Zhanyu Wang , Jinsong Su , Longyue Wang

While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to high computational and memory demands in real-world…

Computation and Language · Computer Science 2024-02-27 Chenglin Li , Qianglong Chen , Liangyue Li , Caiyu Wang , Yicheng Li , Zulong Chen , Yin Zhang