相关论文: Lossless Prompt Compression via Dictionary-Encodin…

Large language models (LLMs) have emerged as a cornerstone in real-world applications with lengthy streaming inputs (e.g., LLM-driven agents). However, existing LLMs, pre-trained on sequences with a restricted maximum length, cannot process…

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…

Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. Leveraging LCLMs' ability to natively ingest and process entire…

Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices…

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches…

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has…

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that…

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

It is well-known in the field of lossless data compression that probabilistic next-symbol prediction can be used to compress sequences of symbols. Deep neural networks are able to capture rich dependencies in data, offering a powerful means…

The relentless expansion of scientific literature presents significant challenges for navigation and knowledge discovery. Within Research Information Retrieval, established tasks such as text summarization and classification remain crucial…

Limited by the context window size of Large Language Models(LLMs), handling various tasks with input tokens exceeding the upper limit has been challenging, whether it is a simple direct retrieval task or a complex multi-hop reasoning task.…

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep…

The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the…

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency. We introduce a…

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

This study evaluates the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context. We identify the tendency for computational errors to increase under long-context when employing certain…

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…