English
Related papers

Related papers: Smaller, Weaker, Yet Better: Training LLM Reasoner…

200 papers

Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work…

Computation and Language · Computer Science 2024-01-02 Hongkun Hao , Long Zhou , Shujie Liu , Jinyu Li , Shujie Hu , Rui Wang , Furu Wei

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Computation and Language · Computer Science 2026-05-12 Ömer Faruk Akgül , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

Factual consistency evaluation is often conducted using Natural Language Inference (NLI) models, yet these models exhibit limited success in evaluating summaries. Previous work improved such models with synthetic training data. However, the…

Computation and Language · Computer Science 2023-10-20 Zorik Gekhman , Jonathan Herzig , Roee Aharoni , Chen Elkind , Idan Szpektor

We study the reasoning behavior of large language models (LLMs) under limited computation budgets. In such settings, producing useful partial solutions quickly is often more practical than exhaustive reasoning, which incurs high inference…

Computation and Language · Computer Science 2026-04-21 Xuanming Zhang , Shwan Ashrafi , Aziza Mirsaidova , Amir H. Rezaeian , Miguel Ballesteros , Lydia B. Chilton , Zhou Yu , Dan Roth

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Artificial Intelligence · Computer Science 2026-03-24 Zhuojie Yang , Wentao Wan , Keze Wang

Large language models (LLMs) have demonstrated strong performance on coding tasks such as generation, completion and repair, but their ability to handle complex symbolic reasoning over code still remains underexplored. We introduce the task…

Software Engineering · Computer Science 2025-09-17 Daniel Koh , Yannic Noller , Corina S. Pasareanu , Adrians Skapars , Youcheng Sun

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can…

Computation and Language · Computer Science 2026-03-06 Amirabbas Afzali , Myeongho Jeon , Maria Brbic

Imbalanced classification and spurious correlation are common challenges in data science and machine learning. Both issues are linked to data imbalance, with certain groups of data samples significantly underrepresented, which in turn would…

Machine Learning · Statistics 2026-02-10 Ryumei Nakada , Yichen Xu , Lexin Li , Linjun Zhang

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

Computation and Language · Computer Science 2023-02-08 Amirkeivan Mohtashami , Mauro Verzetti , Paul K. Rubenstein

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning…

Computation and Language · Computer Science 2025-10-07 Xiangchi Yuan , Xiang Chen , Tong Yu , Dachuan Shi , Can Jin , Wenke Lee , Saayan Mitra

State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…

Computation and Language · Computer Science 2023-06-29 Parikshit Bansal , Amit Sharma

Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is…

Computation and Language · Computer Science 2024-07-23 Yinheng Li , Rogerio Bonatti , Sara Abdali , Justin Wagle , Kazuhito Koishida

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…

Computation and Language · Computer Science 2025-04-18 Linda He , Jue Wang , Maurice Weber , Shang Zhu , Ben Athiwaratkun , Ce Zhang

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

Computation and Language · Computer Science 2023-09-19 Dawei Zhu , Xiaoyu Shen , Marius Mosbach , Andreas Stephan , Dietrich Klakow

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has…

Computation and Language · Computer Science 2023-12-19 Marija Šakota , Maxime Peyrard , Robert West

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are…

Computation and Language · Computer Science 2025-06-17 Bohan Zhang , Xiaokang Zhang , Jing Zhang , Jifan Yu , Sijia Luo , Jie Tang

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…

Information Retrieval · Computer Science 2024-08-27 Cong Xu , Zhangchi Zhu , Mo Yu , Jun Wang , Jianyong Wang , Wei Zhang

Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose…

Computation and Language · Computer Science 2025-08-27 Sirui Chen , Changxin Tian , Binbin Hu , Kunlong Chen , Ziqi Liu , Zhiqiang Zhang , Jun Zhou

As world knowledge advances and new task schemas emerge, Continual Learning (CL) becomes essential for keeping Large Language Models (LLMs) current and addressing their shortcomings. This process typically involves continual instruction…

Machine Learning · Computer Science 2024-12-17 Haokun Zhao , Haixia Han , Jie Shi , Chengyu Du , Jiaqing Liang , Yanghua Xiao