相关论文: COMI: Coarse-to-fine Context Compression via Margi…

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…

Retrieval-Augmented Large Language Models (RALMs) have made significant strides in enhancing the accuracy of generated responses.However, existing research often overlooks the data quality issues within retrieval results, often caused by…

Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool,…

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…

Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…

Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore, context compression is necessary to enhance its accuracy and efficiency. Existing context…

Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded Mini-sequence Inference (MOM), a method that partitions…

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length. Existing compression…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…

Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval…

Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many demonstrations, and SFT incurs training overhead while…

Generating high-quality answers consistently by providing contextual information embedded in the prompt passed to the Large Language Model (LLM) is dependent on the quality of information retrieval. As the corpus of contextual information…

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Context Learning (ICL). Increasing the number of examples, called…

Recent advancements in large language models (LLMs) have highlighted the importance of extending context lengths for handling complex tasks. While traditional methods for training on long contexts often use filtered long documents, these…

How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured…

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large…