中文
相关论文

相关论文: Beyond Imitation: Learning Key Reasoning Steps fro…

200 篇论文

Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small…

计算与语言 · 计算机科学 2025-05-28 Xinghao Chen , Zhijing Sun , Wenjin Guo , Miaoran Zhang , Yanjun Chen , Yirong Sun , Hui Su , Yijie Pan , Dietrich Klakow , Wenjie Li , Xiaoyu Shen

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long…

计算与语言 · 计算机科学 2025-06-19 Zhaoyang Wang , Jinqi Jiang , Tian Qiu , Hui Liu , Xianfeng Tang , Huaxiu Yao

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…

计算与语言 · 计算机科学 2026-04-20 Yao Chen , Jiawei Sheng , Wenyuan Zhang , Tingwen Liu

Chain-of-thought (CoT) distillation aims to enhance small language models' (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However, existing work underestimates rationale quality, focusing…

计算与语言 · 计算机科学 2025-09-30 Jianzhi Yan , Le Liu , Youcheng Pan , Shiwei Chen , Yang Xiang , Buzhou Tang

While chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks, it struggles in scientific domains where even advanced models often produce incorrect or superficial…

计算与语言 · 计算机科学 2025-10-17 Kehua Feng , Keyan Ding , Zhihui Zhu , Lei Liang , Qiang Zhang , Huajun Chen

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

计算与语言 · 计算机科学 2023-09-01 Peifeng Wang , Zhengyang Wang , Zheng Li , Yifan Gao , Bing Yin , Xiang Ren

Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting. Recently, studies have proposed a Knowledge Distillation (KD) approach, reasoning distillation,…

计算与语言 · 计算机科学 2024-10-14 Hojae Lee , Junho Kim , SangKeun Lee

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Chain-of-thought (CoT) distillation allows a large language model (LLM) to guide a small language model (SLM) in reasoning tasks. Existing methods train the SLM to learn the long rationale in one iteration, resulting in two issues: 1) Long…

计算与语言 · 计算机科学 2025-05-27 Xiao Chen , Sihang Zhou , Ke Liang , Xiaoyu Sun , Xinwang Liu

Reasoning-capable language models achieve state-of-the-art performance in diverse complex tasks by generating long, explicit Chain-of-Thought (CoT) traces. While recent works show that base models can acquire such reasoning traces via…

Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous works simply fine-tune student models on teachers' generated…

计算与语言 · 计算机科学 2024-05-31 Chengwei Dai , Kun Li , Wei Zhou , Songlin Hu

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…

人工智能 · 计算机科学 2026-02-09 Ruichen Zhang , Rana Muhammad Shahroz Khan , Zhen Tan , Dawei Li , Song Wang , Tianlong Chen

Chain-of-Thought (CoT) significantly enhances formal reasoning capabilities in Large Language Models (LLMs) by training them to explicitly generate intermediate reasoning steps. While LLMs readily benefit from such techniques, improving…

While large language models (LLMs) excel in various natural language processing tasks, their huge size and the inaccessibility of parameters present challenges for practical deployment. Previous studies try to distill task-specific ability…

计算与语言 · 计算机科学 2024-03-21 Xuekai Zhu , Biqing Qi , Kaiyan Zhang , Xinwei Long , Zhouhan Lin , Bowen Zhou

Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length of reasoning steps in prompts remains largely unknown. To…

计算与语言 · 计算机科学 2024-06-25 Mingyu Jin , Qinkai Yu , Dong Shu , Haiyan Zhao , Wenyue Hua , Yanda Meng , Yongfeng Zhang , Mengnan Du

Chain-of-Thought (CoT) prompting is a widely used method to improve the reasoning capability of Large Language Models (LLMs). More recently, CoT has been leveraged in Knowledge Distillation (KD) to transfer reasoning capability from a…

计算与语言 · 计算机科学 2025-11-10 Cong-Thanh Do , Rama Doddipatla , Kate Knill

Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied to the model size,…

机器学习 · 计算机科学 2023-05-19 Kumar Shridhar , Alessandro Stolfo , Mrinmaya Sachan

Large language models (LLMs) excel at reasoning tasks but are expensive to deploy. Thus small language models (SLMs) are fine-tuned on CoT data generated by LLMs to copy LLMs' abilities. However, these CoT data may include noisy rationales…

计算与语言 · 计算机科学 2025-09-10 Hongyan Xie , Yitong Yao , Yikun Ban , Zixuan Huang , Deqing Wang , Zhenhe Wu , Haoxiang Su , Chao Wang , Shuangyong Song

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…

计算与语言 · 计算机科学 2025-05-28 Haritz Puerto , Tilek Chubakov , Xiaodan Zhu , Harish Tayyar Madabushi , Iryna Gurevych

Eliciting "chain of thought" (CoT) rationales -- sequences of token that convey a "reasoning" process -- has been shown to consistently improve LLM performance on tasks like question answering. More recent efforts have shown that such…

计算与语言 · 计算机科学 2024-10-01 Somin Wadhwa , Silvio Amir , Byron C. Wallace
‹ 上一页 1 2 3 10 下一页 ›