English
Related papers

Related papers: NAIL: Lexical Retrieval Indices with Efficient Non…

200 papers

Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show…

Computation and Language · Computer Science 2021-02-17 Yixuan Su , Deng Cai , Yan Wang , David Vandyke , Simon Baker , Piji Li , Nigel Collier

Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. However, existing approaches typically implement iterative refinement at the application or prompting…

Computation and Language · Computer Science 2024-10-15 Yuxi Xie , Anirudh Goyal , Xiaobao Wu , Xunjian Yin , Xiao Xu , Min-Yen Kan , Liangming Pan , William Yang Wang

Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a pre-computed document similarity graph in reranking.…

Information Retrieval · Computer Science 2025-12-23 Soyoung Yoon , Jongho Kim , Daeyong Kwon , Avishek Anand , Seung-won Hwang

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

Computation and Language · Computer Science 2018-07-27 Arindam Chowdhury , Lovekesh Vig

Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. This…

Computation and Language · Computer Science 2025-05-29 Xiang Fei , Jinghui Lu , Qi Sun , Hao Feng , Yanjie Wang , Wei Shi , An-Lan Wang , Jingqun Tang , Can Huang

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

Information Retrieval · Computer Science 2020-10-21 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Min Zhang , Shaoping Ma

Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with…

Computation and Language · Computer Science 2020-04-08 Zdeněk Kasner , Jindřich Libovický , Jindřich Helcl

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Computation and Language · Computer Science 2025-09-26 Manlai Liang , Mandi Liu , Jiangzhou Ji , Huaijun Li , Haobo Yang , Yaohan He , Jinlong Li

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

Machine Learning · Computer Science 2023-07-28 Or Sharir , Anima Anandkumar

When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a…

Machine Learning · Computer Science 2022-06-20 Jinlin Xiang , Eli Shlizerman

Audio-LLM introduces audio modality into a large language model (LLM) to enable a powerful LLM to recognize, understand, and generate audio. However, during speech recognition in noisy environments, we observed the presence of illusions and…

Sound · Computer Science 2024-08-20 Yangze Li , Xiong Wang , Songjun Cao , Yike Zhang , Long Ma , Lei Xie

Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in…

Computation and Language · Computer Science 2024-07-03 Hao Wang , Tetsuro Morimura , Ukyo Honda , Daisuke Kawahara

A visually rich document (VRD) utilizes visual features along with linguistic cues to disseminate information. Training a custom extractor that identifies named entities from a document requires a large number of instances of the target…

Computation and Language · Computer Science 2024-04-02 Ritesh Sarkhel , Xiaoqi Ren , Lauro Beltrao Costa , Guolong Su , Vincent Perot , Yanan Xie , Emmanouil Koukoumidis , Arnab Nandi

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to…

Computation and Language · Computer Science 2024-05-06 Qingqing Cao , Sewon Min , Yizhong Wang , Hannaneh Hajishirzi

The fast-growing large scale language models are delivering unprecedented performance on almost all natural language processing tasks. However, the effectiveness of large language models are reliant on an exponentially increasing number of…

Computation and Language · Computer Science 2024-07-08 Longwei Zou , Qingyang Wang , Han Zhao , Jiangang Kong , Yi Yang , Yangdong Deng

The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference, focusing on hardware-imposed bottlenecks in…

Hardware Architecture · Computer Science 2025-11-17 Michael Davies , Neal Crago , Karthikeyan Sankaralingam , Christos Kozyrakis

Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to…

Computation and Language · Computer Science 2025-05-27 Zhengliang Shi , Yuhan Wang , Lingyong Yan , Pengjie Ren , Shuaiqiang Wang , Dawei Yin , Zhaochun Ren

Transformers are central to recent successes in natural language processing and computer vision. Transformers have a mostly uniform backbone where layers alternate between feed-forward and self-attention in order to build a deep network.…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

In-context learning (ICL), a property demonstrated by transformer-based sequence models, refers to the automatic inference of an input-output mapping based on examples of the mapping provided as context. ICL requires no explicit learning,…

Signal Processing · Electrical Eng. & Systems 2024-11-12 Zihang Song , Osvaldo Simeone , Bipin Rajendran