English
Related papers

Related papers: Self-training Language Models for Arithmetic Reaso…

200 papers

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that…

Machine Learning · Computer Science 2026-05-05 Lucas Dionisopoulos , Nicklas Majamaki , Prithviraj Ammanabrolu

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

Computation and Language · Computer Science 2023-10-02 Ping Yu , Tianlu Wang , Olga Golovneva , Badr AlKhamissi , Siddharth Verma , Zhijing Jin , Gargi Ghosh , Mona Diab , Asli Celikyilmaz

Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, acquiring high-quality reasoning traces is often costly and time-consuming. Hence, the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Qihuang Zhong , Liang Ding , Wenjie Xuan , Juhua Liu , Bo Du , Dacheng Tao

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on…

Computation and Language · Computer Science 2020-12-16 Faeze Brahman , Vered Shwartz , Rachel Rudinger , Yejin Choi

Prediction model training is often hindered by limited access to individual-level data due to privacy concerns and logistical challenges, particularly in biomedical research. Resampling-based self-training presents a promising approach for…

Methodology · Statistics 2025-03-18 Buxin Su , Jiaoyang Huang , Jin Jin , Bingxin Zhao

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

The goal of this paper is to investigate the connection between the performance gain that can be obtained by selftraining and the similarity between the corpora used in this approach. Self-training is a semi-supervised technique designed to…

Computation and Language · Computer Science 2016-01-14 Vincent Van Asch , Walter Daelemans

Recent research has shown that rationales, or step-by-step chains of thought, can be used to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented prompting for few-shot in-context learning, where (input ->…

Computation and Language · Computer Science 2022-07-05 Xuezhi Wang , Jason Wei , Dale Schuurmans , Quoc Le , Ed Chi , Denny Zhou

The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formally structured expressions. Yet, current LM…

Rationalization is fundamental to human reasoning and learning. NLP models trained to produce rationales along with predictions, called self-rationalization models, have been investigated for their interpretability and utility to end-users.…

Computation and Language · Computer Science 2022-10-26 Alexis Ross , Matthew E. Peters , Ana Marasović

The use of argumentation in education has been shown to improve critical thinking skills for end-users such as students, and computational models for argumentation have been developed to assist in this process. Although these models are…

Computation and Language · Computer Science 2023-07-31 Camélia Guerraoui , Paul Reisert , Naoya Inoue , Farjana Sultana Mim , Shoichi Naito , Jungmin Choi , Irfan Robbani , Wenzhi Wang , Kentaro Inui

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy…

Computation and Language · Computer Science 2023-03-08 Xuezhi Wang , Jason Wei , Dale Schuurmans , Quoc Le , Ed Chi , Sharan Narang , Aakanksha Chowdhery , Denny Zhou

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Artificial Intelligence · Computer Science 2024-11-25 Haolin Chen , Yihao Feng , Zuxin Liu , Weiran Yao , Akshara Prabhakar , Shelby Heinecke , Ricky Ho , Phil Mui , Silvio Savarese , Caiming Xiong , Huan Wang

Large language models (LLMs) have improved significantly in their reasoning through extensive training on massive datasets. However, relying solely on additional data for improvement is becoming increasingly impractical, highlighting the…

Computation and Language · Computer Science 2025-10-01 Gaurav Srivastava , Zhenyu Bi , Meng Lu , Xuan Wang

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

Artificial Intelligence · Computer Science 2025-08-08 Chang Tian , Matthew B. Blaschko , Mingzhe Xing , Xiuxing Li , Yinliang Yue , Marie-Francine Moens

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Artificial Intelligence · Computer Science 2026-05-26 Andreas Opedal , Francesco Ignazio Re , Abulhair Saparov , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions.…

Computation and Language · Computer Science 2024-07-02 Wenhao Zhu , Shujian Huang , Fei Yuan , Shuaijie She , Jiajun Chen , Alexandra Birch