paper-with-me

Papers

LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning

2024-12-18 · Yansheng Mao, Jiaqi Li, Fanxu Meng, Jing Xiong, Zilong Zheng, Muhan Zhang

Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine-Tuning (LIFT) for long context modeling, a novel framework that enhances LLM performance on long-context tasks by adapting model parameters to the context at test time. LIFT enables efficient processing of lengthy inputs without the computational burden of offline long-context adaptation, and can improve the long-context capabilities of arbitrary short-context models. The framework is further enhanced by integrating in-context learning and pre-LIFT supervised fine-tuning. The combination of in-context learning and LIFT enables short-context models like Llama 3 to handle arbitrarily long contexts and consistently improves their performance on popular long-context benchmarks like LooGLE and LongBench. We also provide a comprehensive analysis of the strengths and limitations of LIFT on long context understanding, offering valuable directions for future research.

📄 PDF Abstract BibTeX arXiv:2412.13626

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningLong-Context Understanding

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

LIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning

2025-02-20 · Yansheng Mao, Yufei Xu, Jiaqi Li, Fanxu Meng 외

Long context understanding remains challenging for large language models due to their limited context windows. This paper presents Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can impro…

In-Context LearningLong-Context UnderstandingMemorization

LiFT: Does Instruction Fine-Tuning Improve In-Context Learning for Longitudinal Modelling by Large Language Models?

2026-03-25 · Iqra Ali, Talia Tseriotou, Mahmud Elahi Akhter, Yuxiang Zhou 외 arxiv

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where mode…

LiftVSR: Lifting Image Diffusion to Video Super-Resolution via Hybrid Temporal Modeling with Only 4$\times$RTX 4090s

2025-06-10 · Xijun Wang, Xin Li, Bingchen Li, Zhibo Chen

Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing metho…

Super-ResolutionVideo Super-Resolution

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

2025-07-20 · Yifei Wang arxiv

Reasoning distillation has emerged as an effective approach to enhance the reasoning capabilities of smaller language models. However, the impact of large-scale reasoning distillation on other critical abilities, particu…

Long-Context Understanding

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray

2025-02-07 · Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang 외

Establishing the long-context capability of large vision-language models is crucial for video understanding, high-resolution image understanding, multi-modal agents and reasoning. We introduce Long-VITA, a simple yet eff…

4kGeneral KnowledgeGPULanguage Modeling+3