paper-with-me

홈 › Papers

LLM Post-Training: A Deep Dive into Reasoning Large Language Models

2025-02-28 · Komal Kumar, Tajamul Ashraf, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Phillip H. S. Torr, Fahad Shahbaz Khan, Salman Khan

Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the research community is now increasingly shifting focus toward post-training techniques to achieve further breakthroughs. While pretraining provides a broad linguistic foundation, post-training methods enable LLMs to refine their knowledge, improve reasoning, enhance factual accuracy, and align more effectively with user intents and ethical considerations. Fine-tuning, reinforcement learning, and test-time scaling have emerged as critical strategies for optimizing LLMs performance, ensuring robustness, and improving adaptability across various real-world tasks. This survey provides a systematic exploration of post-training methodologies, analyzing their role in refining LLMs beyond pretraining, addressing key challenges such as catastrophic forgetting, reward hacking, and inference-time trade-offs. We highlight emerging directions in model alignment, scalable adaptation, and inference-time reasoning, and outline future research directions. We also provide a public repository to continually track developments in this fast-evolving field: https://github.com/mbzuai-oryx/Awesome-LLM-Post-training.

📄 PDF Abstract BibTeX arXiv:2502.21321

Code (1)

mbzuai-oryx/awesome-llm-post-training 공식 구현

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Focus 설명 없음

Similar Papers 제목 키워드 기반

AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models

2026-06-12 · Hui Geng, Yi Su, Han Yin, Tianjiao Wan 외 arxiv

Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning. A practical way to improve such capabilities is post-t…

Exploration-Driven Optimization for Test-Time Large Language Model Reasoning

2026-05-11 · Changhao Li, Yuchen Zhuang, Chenxiao Gao, Haotian Sun 외 arxiv

Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods …

Reinforcement Learning

Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

2026-07-01 · Shijie Li, Yilin Gao, Siyuan Yang, Tieyuan Chen 외 hf

Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous…

Visual Reasoning

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

2025-04-14 · Ming Li, Yanhong Li, Ziyue Li, Tianyi Zhou

As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics remains largely unexplored. In this paper, …

Instruction Following

Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention

2026-03-02 · Wenye Lin, Kai Han arxiv

Injecting new reasoning knowledge into Large Language Models (LLMs) via post-training often induces catastrophic forgetting. Recent studies emphasize the importance of on-policy data but suggest that KL-divergence fails …

Reinforcement Learning