Key points are not available for this paper at this time.
Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose a novel approach to address this problem by learning contexts offline through context compression and in-domain parameter-efficient finetuning. Our method enables an LLM to create a concise representation of the original context and efficiently retrieve relevant information to answer questions accurately. We introduce LLoCO, a technique that combines context compression, retrieval, and parameter-efficient finetuning using LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens. We evaluate our approach on several long-context question-answering datasets, demonstrating that LLoCO significantly outperforms in-context learning while using 30 fewer tokens during inference. LLoCO achieves up to 7. 62 speed-up and substantially reduces the cost of long document question answering, making it a promising solution for efficient long context processing. Our code is publicly available at https: //github. com/jeffreysijuntan/lloco.
Building similarity graph...
Analyzing shared references across papers
Loading...
Sijun Tan
Xiuyu Li
Shishir G. Patil
Building similarity graph...
Analyzing shared references across papers
Loading...
Tan et al. (Thu,) studied this question.
www.synapsesocial.com/papers/68e6f968b6db643587673b5d — DOI: https://doi.org/10.48550/arxiv.2404.07979
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: