Related papers: Read As Human: Compressing Context via Paralleliza…
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…
Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks…
Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long…
The nonliteral interpretation of a text is hard to be understood by machine models due to its high context-sensitivity and heavy usage of figurative language. In this study, inspired by human reading comprehension, we propose a novel,…
Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…
Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning…
Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely on complex compression modules or compression-specific…
Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…
Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…
Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…
Large Language Models (LLMs) continue to advance natural language processing with their ability to generate human-like text across a range of tasks. Despite the remarkable success of LLMs in Natural Language Processing (NLP), their…
Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…
Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models…
Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…
In this paper, we explore the potential of using a large language model (LLM) to understand the driving environment in a human-like manner and analyze its ability to reason, interpret, and memorize when facing complex scenarios. We argue…
Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive…
Recent studies have found that summaries generated by large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. Therefore, we study an LLM-as-reference…
To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…
Large Language Models (LLMs) have demonstrated remarkable capabilities in leveraging extensive external knowledge to enhance responses in multi-turn and agentic applications, such as retrieval-augmented generation (RAG). However, processing…