paper-with-me

Papers

DAST: Difficulty-Aware Self-Training on Large Language Models

2025-03-12 · Boyang Xue, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Hongling Xu, Fei Mi, Yasheng Wang, Lifeng Shang, Qun Liu, Kam-Fai Wong

Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability. Therefore, this work proposes a difficulty-aware self-training (DAST) framework that focuses on improving both the quantity and quality of self-generated responses on challenging queries during self-training. DAST is specified in three components: 1) sampling-based difficulty level estimation, 2) difficulty-aware data augmentation, and 3) the self-training algorithm using SFT and DPO respectively. Experiments on mathematical tasks demonstrate the effectiveness and generalization of DAST, highlighting the critical role of difficulty-aware strategies in advancing LLM self-training.

📄 PDF Abstract BibTeX arXiv:2503.09029

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

DPO 설명 없음
SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models

2025-03-06 · Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi 외

Recent advancements in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking-generating redundant reasoning steps for simple proble…

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

2025-05-22 · Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee 외

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often…

Diversity

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

2020-06-29 · ICLR 2021 1 · Kaidi Cao, Yining Chen, Junwei Lu, Nikos Arechiga 외

Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms…

Deep LearningImage Classification

Mind the Long Tail: Understanding the Difficulty of Delay Detection in Business Processes

2026-08-14 · Keyvan Amiri Elyasi, Lukas Kirchdorfer, Heiner Stuckenschmidt arxiv

The early detection of delayed cases in business processes is a critical capability for organizations. Predictive process monitoring (PPM) supports this task by using historical event logs to predict the remaining time o…

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback

2025-10-03 · Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu 외 arxiv

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In …

Reinforcement Learning