相关论文: SCoder: Iterative Self-Distillation for Bootstrapp…

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge amounts of data, increasing the computational time and cost. To address this, dataset…

Dataset distillation compresses a large training set into a small synthetic set that preserves downstream training utility. While most existing methods target training networks from scratch, modern visual transfer learning often uses frozen…

Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a more fundamental…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

Large machine-learning training datasets can be distilled into small collections of informative synthetic data samples. These synthetic sets support efficient model learning and reduce the communication cost of data sharing. Thus,…

Synthesizing high-quality instruction data from unsupervised text is a promising paradigm for training large language models (LLMs), yet automated methods for this task still exhibit significant limitations in the diversity and difficulty…

Competitive programming poses a significant challenge for Code LLMs. While recent models have shown promise, they heavily rely on finite real-world data, raising concerns about scalability and contamination. In this paper, we investigate a…

Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation, task evaluation, fine-tuning, distillation, and other…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Large language models (LLMs) have achieved remarkable progress in mathematical reasoning, but this ability is not equally accessible across languages. Especially low-resource languages exhibit much lower reasoning performance. To address…

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

The enhancement of mathematical capabilities in large language models (LLMs) fosters new developments in mathematics education within primary and secondary schools, particularly as they relate to intelligent tutoring systems. However, LLMs…

Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training…

Small Language models (SLMs) offer an efficient and accessible alternative to Large Language Models (LLMs), delivering strong performance while using far fewer resources. We introduce a simple and effective framework for pretraining SLMs…

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…

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning,…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally…

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor…