English
Related papers

Related papers: Hint Tuning: Less Data Makes Better Reasoners

200 papers

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…

Artificial Intelligence · Computer Science 2026-01-16 Michael R. Metel , Yufei Cui , Boxing Chen , Prasanna Parthasarathi

Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized…

Computation and Language · Computer Science 2025-02-05 Shengmin Piao , Sanghyun Park

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing…

Computation and Language · Computer Science 2025-09-30 Xin Liu , Lu Wang

Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reasoning traces and inadequate adaptability to problem…

Artificial Intelligence · Computer Science 2025-05-27 Yifan Wu , Jingze Shi , Bingheng Wu , Jiayi Zhang , Xiaotian Lin , Nan Tang , Yuyu Luo

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Computation and Language · Computer Science 2024-10-04 Constanza Fierro , Jiaang Li , Anders Søgaard

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

Computation and Language · Computer Science 2026-03-25 Richard J. Young

A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1,…

Computation and Language · Computer Science 2025-12-24 Cehao Yang , Xueyuan Lin , Xiaojun Wu , Chengjin Xu , Xuhui Jiang , Honghao Liu , Hui Xiong , Jian Guo

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Computation and Language · Computer Science 2024-07-12 Changyu Chen , Xiting Wang , Ting-En Lin , Ang Lv , Yuchuan Wu , Xin Gao , Ji-Rong Wen , Rui Yan , Yongbin Li

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially increases inference overhead, making efficiency a critical…

Computation and Language · Computer Science 2025-05-20 Jiajie Zhang , Nianyi Lin , Lei Hou , Ling Feng , Juanzi Li

Large Language Models (LLMs) excel at reasoning, traditionally requiring high-quality large-scale data and extensive training. Recent works reveal a very appealing Less-Is-More phenomenon where very small, carefully curated high-quality…

Machine Learning · Computer Science 2026-04-22 Rapheal Huang , Weilong Guo

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…

Information Retrieval · Computer Science 2025-07-01 Chris Samarinas , Hamed Zamani

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

Computation and Language · Computer Science 2025-05-26 Razvan-Gabriel Dumitru , Darius Peteleaza , Vikas Yadav , Liangming Pan

Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to…

Computation and Language · Computer Science 2025-11-05 Jingxian Xu , Mengyu Zhou , Weichang Liu , Hanbing Liu , Shi Han , Dongmei Zhang

With the rapid development of deep learning, large language models have shown strong capabilities in complex reasoning tasks such as mathematical equation solving. However, their substantial computational and storage costs hinder practical…

Machine Learning · Computer Science 2025-11-25 Fengming Yu , Qingyu Meng , Haiwei Pan , Kejia Zhang

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

Machine Learning · Computer Science 2026-01-22 Keyu Lv , Manyi Zhang , Xiaobo Xia , Jingchen Ni , Shannan Yan , Xianzhi Yu , Lu Hou , Chun Yuan , Haoli Bai

Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds the…

Machine Learning · Computer Science 2025-10-13 Xinyi Wang , Jinyi Han , Zishang Jiang , Tingyun Li , Jiaqing Liang , Sihang Jiang , Zhaoqian Dai , Shuguang Ma , Fei Yu , Yanghua Xiao

We study whether lightweight symbolic reasoning supervision can improve fix type classification in compact automated program repair models. Small code models are attractive for resource-constrained settings, but they typically produce only…

Machine Learning · Computer Science 2026-01-19 Aanand Balasubramanian , Sashank Silwal

Recent works have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks, step-by-step. However, prompt-based CoT methods are dependent on very large models such as GPT-3 175B which are…

Computation and Language · Computer Science 2023-06-14 Namgyu Ho , Laura Schmid , Se-Young Yun