45 citations · 193 across the 32 of their papers we have counts for
27 papers · 1 filter
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
Xin Cheng, Xun Wang, Xingxing Zhang +5
This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditio…
ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
Shaoguang Mao, Yuzhe Cai, Yan Xia +5
This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a ver…
In-context Autoencoder for Context Compression in a Large Language Model
Tao Ge, Jing Hu, Lei Wang +3
We propose the In-context Autoencoder (ICAE), leveraging the power of a large language model (LLM) to compress a long context into short compact memory slots that can be directly c…
Smart Word Suggestions for Writing Assistance
Chenshuo Wang, Shaoguang Mao, Tao Ge +5
Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces "Smart Word Suggestions" (SWS) task and benchmark.…
Inference with Reference: Lossless Acceleration of Large Language Models
Nan Yang, Tao Ge, Liang Wang +5
We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identi…
Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory
Guangyue Peng, Tao Ge, Wen Luo +2
Semiparametric language models (LMs) have shown promise in various Natural Language Processing (NLP) tasks. However, they utilize non-parametric memory as static storage, which lac…
Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Xun Wang, Tao Ge, Allen Mao +3
We introduce \textsc{PoliteRewrite} -- a dataset for polite language rewrite which is a novel sentence rewrite task. Compared with previous text style transfer tasks that can be mo…
Extensible Prompts for Language Models on Zero-shot Language Style Customization
Tao Ge, Jing Hu, Li Dong +5
We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible v…
Lossless Acceleration for Seq2seq Generation with Aggressive Decoding
Tao Ge, Heming Xia, Xin Sun +2
We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding. Unlike the previous efforts (e.g., non-autoregressive decoding) speedi…
Text Revision by On-the-Fly Representation Optimization
Jingjing Li, Zichao Li, Tao Ge +2
Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attribu…
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
Heming Xia, Tao Ge, Peiyi Wang +3
We propose Speculative Decoding (SpecDec), for the first time ever, to formally study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding. Specu…
EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation
Tao Ge, Si-Qing Chen, Furu Wei
We introduce EdgeFormer -- a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parame…
A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model
Xin Sun, Tao Ge, Shuming Ma +3
Synthetic data construction of Grammatical Error Correction (GEC) for non-English languages relies heavily on human-designed and language-specific rules, which produce limited erro…
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
Canwen Xu, Wangchunshu Zhou, Tao Ge +3
Recent studies on compression of pretrained language models (e.g., BERT) usually use preserved accuracy as the metric for evaluation. In this paper, we propose two new metrics, lab…
Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
Xin Sun, Tao Ge, Furu Wei +1
In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD…
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
Canwen Xu, Wangchunshu Zhou, Tao Ge +3
Cant is important for understanding advertising, comedies and dog-whistle politics. However, computational research on cant is hindered by a lack of available datasets. In this pap…
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
Wangchunshu Zhou, Tao Ge, Canwen Xu +2
In this paper, we generalize text infilling (e.g., masked language models) by proposing Sequence Span Rewriting (SSR) as a self-supervised sequence-to-sequence (seq2seq) pre-traini…
Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
Mengyun Chen, Tao Ge, Xingxing Zhang +2
We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (…
BERT Loses Patience: Fast and Robust Inference with Early Exit
Wangchunshu Zhou, Canwen Xu, Tao Ge +3
In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the ef…
Parallel Data Augmentation for Formality Style Transfer
Yi Zhang, Tao Ge, Xu Sun
The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data. In this paper, we study how to augment parallel data and propose novel and…
Scheduled DropHead: A Regularization Method for Transformer Models
Wangchunshu Zhou, Tao Ge, Ke Xu +2
In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer…
Self-Adversarial Learning with Comparative Discrimination for Text Generation
Wangchunshu Zhou, Tao Ge, Ke Xu +2
Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated…
Fact-aware Sentence Split and Rephrase with Permutation Invariant Training
Yinuo Guo, Tao Ge, Furu Wei
Sentence Split and Rephrase aims to break down a complex sentence into several simple sentences with its meaning preserved. Previous studies tend to address the issue by seq2seq le…
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
Canwen Xu, Wangchunshu Zhou, Tao Ge +2
In this paper, we propose a novel model compression approach to effectively compress BERT by progressive module replacing. Our approach first divides the original BERT into several…