中文
相关论文

相关论文: Retrieval and Multi-Hop Reasoning in 1M-Token Cont…

200 篇论文

Large language models have recently made tremendous progress in a variety of aspects, e.g., cross-task generalization, instruction following. Comprehensively evaluating the capability of large language models in multiple tasks is of great…

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…

计算与语言 · 计算机科学 2024-08-28 Jiaming Tang , Yilong Zhao , Kan Zhu , Guangxuan Xiao , Baris Kasikci , Song Han

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context…

软件工程 · 计算机科学 2026-02-20 Kishan Maharaj , Nandakishore Menon , Ashita Saxena , Srikanth Tamilselvam

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…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Payal Fofadiya , Sunil Tiwari

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes…

计算与语言 · 计算机科学 2024-10-04 Yung-Sung Chuang , Linlu Qiu , Cheng-Yu Hsieh , Ranjay Krishna , Yoon Kim , James Glass

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

机器学习 · 计算机科学 2024-11-07 Quinn Leng , Jacob Portes , Sam Havens , Matei Zaharia , Michael Carbin

Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to…

计算与语言 · 计算机科学 2023-08-17 Hritik Bansal , Karthik Gopalakrishnan , Saket Dingliwal , Sravan Bodapati , Katrin Kirchhoff , Dan Roth

Large Language Models (LLMs), constrained by limited context windows, often face significant performance degradation when reasoning over long contexts. To address this, Retrieval-Augmented Generation (RAG) retrieves and reasons over chunks…

计算与语言 · 计算机科学 2025-11-04 Jiani Guo , Zuchao Li , Jie Wu , Qianren Wang , Yun Li , Lefei Zhang , Hai Zhao , Yujiu Yang

Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as…

机器学习 · 计算机科学 2026-03-03 Chenxiao Yang , Nathan Srebro , Zhiyuan Li

We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW), which extends the maximum context lengths of language models, e.g., 2048 for LLaMA, by harnessing window-wise…

计算与语言 · 计算机科学 2023-05-25 Kejuan Yang , Xiao Liu , Kaiwen Men , Aohan Zeng , Yuxiao Dong , Jie Tang

The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strategy for this problem, as it enables LLMs to make selective…

计算与语言 · 计算机科学 2025-02-18 Kun Luo , Zheng Liu , Peitian Zhang , Hongjin Qian , Jun Zhao , Kang Liu

This project reproduces and extends the recently proposed ``Recursive Language Models'' (RLMs) framework by Zhang et al. (2026). This framework enables Large Language Models (LLMs) to process near-infinite contexts by offloading the prompt…

计算与语言 · 计算机科学 2026-03-04 Daren Wang

Large Language Models (LLMs) have shown great potential in supporting automated code review due to their impressive capabilities in context understanding and reasoning. However, these capabilities are still limited compared to human-level…

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long…

计算与语言 · 计算机科学 2024-09-27 Zhenmei Shi , Yifei Ming , Xuan-Phi Nguyen , Yingyu Liang , Shafiq Joty

In this study, we introduced a new benchmark consisting of a curated dataset and a defined evaluation process to assess the compositional reasoning capabilities of large language models within the chemistry domain. We designed and validated…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

计算与语言 · 计算机科学 2024-11-11 Mansi Sakarvadia

Cross-lingual context retrieval (extracting contextual information in one language based on requests in another) is a fundamental aspect of cross-lingual alignment, but the performance and mechanism of it for large language models (LLMs)…

计算与语言 · 计算机科学 2025-10-21 Changjiang Gao , Hankun Lin , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Jiajun Chen , Shujian Huang

Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. Existing long-context extension methods usually need additional training procedures to support…

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned…

计算与语言 · 计算机科学 2025-11-12 Dmitrii Tarasov , Elizaveta Goncharova , Kuznetsov Andrey

Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear. We conduct an empirical study to systematically evaluate…

软件工程 · 计算机科学 2025-12-30 Mootez Saad , Boqi Chen , José Antonio Hernández López , Dániel Varró , Tushar Sharma