In-context autoencoder for context compression in a large language model
We propose the In-context Autoencoder (ICAE) for context compression in a large language
model (LLM). The ICAE has two modules: a learnable encoder adapted with LoRA from an�…
model (LLM). The ICAE has two modules: a learnable encoder adapted with LoRA from an�…
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon
The utilization of long contexts poses a big challenge for large language models due to their
limited context window length. Although the context window can be extended through fine�…
limited context window length. Although the context window can be extended through fine�…
Adapting language models to compress contexts
Transformer-based language models (LMs) are powerful and widely-applicable tools, but
their usefulness is constrained by a finite context window and the expensive computational�…
their usefulness is constrained by a finite context window and the expensive computational�…
Long-context language modeling with parallel context encoding
Extending large language models (LLMs) to process longer inputs is crucial for numerous
applications. However, the considerable computational cost of transformers, coupled with�…
applications. However, the considerable computational cost of transformers, coupled with�…
Compressing context to enhance inference efficiency of large language models
Large language models (LLMs) achieved remarkable performance across various tasks.
However, they face challenges in managing long documents and extended conversations�…
However, they face challenges in managing long documents and extended conversations�…
Llmlingua: Compressing prompts for accelerated inference of large language models
Large language models (LLMs) have been applied in various applications due to their
astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT)�…
astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT)�…
Fine-tune language models to approximate unbiased in-context learning
In-context learning (ICL) is an astonishing emergent ability of large language models
(LLMs). By presenting a prompt that includes multiple input-output pairs as examples and�…
(LLMs). By presenting a prompt that includes multiple input-output pairs as examples and�…
Label words are anchors: An information flow perspective for understanding in-context learning
In-context learning (ICL) emerges as a promising capability of large language models
(LLMs) by providing them with demonstration examples to perform diverse tasks. However�…
(LLMs) by providing them with demonstration examples to perform diverse tasks. However�…
Parallel context windows for large language models
When applied to processing long text, Large Language Models (LLMs) are limited by their
context window. Existing efforts to address this limitation involve training specialized�…
context window. Existing efforts to address this limitation involve training specialized�…
Longrope: Extending llm context window beyond 2 million tokens
Large context window is a desirable feature in large language models (LLMs). However,
due to high fine-tuning costs, scarcity of long texts, and catastrophic values introduced by�…
due to high fine-tuning costs, scarcity of long texts, and catastrophic values introduced by�…