667 citations · 1.2k across the 29 of their papers we have counts for
30 papers
Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant
Qi Lv, Lei Geng, Ziqiang Cao +4
Softmax with the cross entropy loss is the standard configuration for current neural classification models. The gold score for a target class is supposed to be 1, but it is never r…
The Bidirectional Process Reward Model
Lingyin Zhang, Jun Gao, Xiaoxue Ren +1
Process Reward Models (PRMs), which assign fine-grained scores to intermediate reasoning steps within a solution trajectory, have emerged as a promising approach to enhance the rea…
Interleaved-Modal Chain-of-Thought
Jun Gao, Yongqi Li, Ziqiang Cao +1
Chain-of-Thought (CoT) prompting elicits large language models (LLMs) to produce a series of intermediate reasoning steps before arriving at the final answer. However, when transit…
AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning
Jun Gao, Qian Qiao, Ziqiang Cao +2
In-context learning (ICL) facilitates Large Language Models (LLMs) exhibiting emergent ability on downstream tasks without updating billions of parameters. However, in the area of…
SelfCP: Compressing Over-Limit Prompt via the Frozen Large Language Model Itself
Jun Gao, Ziqiang Cao, Wenjie Li
Long prompt leads to huge hardware costs when using transformer-based Large Language Models (LLMs). Unfortunately, many tasks, such as summarization, inevitably introduce long docu…
Prompt Chaining or Stepwise Prompt? Refinement in Text Summarization
Shichao Sun, Ruifeng Yuan, Ziqiang Cao +2
Large language models (LLMs) have demonstrated the capacity to improve summary quality by mirroring a human-like iterative process of critique and refinement starting from the init…
UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation
Jun Gao, Qi Lv, Zili Wang +3
In-context learning (ICL) enhances the reasoning abilities of Large Language Models (LLMs) by prepending a few demonstrations. It motivates researchers to introduce more examples t…
CoUDA: Coherence Evaluation via Unified Data Augmentation
Dawei Zhu, Wenhao Wu, Yifan Song +3
Coherence evaluation aims to assess the organization and structure of a discourse, which remains challenging even in the era of large language models. Due to the scarcity of annota…
Personalized Large Language Model Assistant with Evolving Conditional Memory
Ruifeng Yuan, Shichao Sun, Yongqi Li +3
With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized se…
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
Lei Geng, Xu Yan, Ziqiang Cao +6
Most biomedical pretrained language models are monolingual and cannot handle the growing cross-lingual requirements. The scarcity of non-English domain corpora, not to mention para…
RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check
Siqi Song, Qi Lv, Lei Geng +2
Chinese Spelling Check (CSC) refers to the detection and correction of spelling errors in Chinese texts. In practical application scenarios, it is important to make CSC models have…
RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
Yang Bai, Min Cao, Daming Gao +5
Text-based person search aims to retrieve the specified person images given a textual description. The key to tackling such a challenging task is to learn powerful multi-modal repr…
Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!
Zecheng Tang, Pinzheng Wang, Keyan Zhou +3
Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between tra…
Text-based Person Search without Parallel Image-Text Data
Yang Bai, Jingyao Wang, Min Cao +4
Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are domi…
Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening
Min Cao, Yang Bai, Jingyao Wang +3
Under the flourishing development in performance, current image-text retrieval methods suffer from -related time complexity, which hinders their application in practice. Targeti…
Few-shot Query-Focused Summarization with Prefix-Merging
Ruifeng Yuan, Zili Wang, Ziqiang Cao +1
Query-focused summarization has been considered as an important extension for text summarization. It aims to generate a concise highlight for a given query. Different from text sum…
FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness
Wenhao Wu, Wei Li, Jiachen Liu +4
Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the…
Visual Subtitle Feature Enhanced Video Outline Generation
Qi Lv, Ziqiang Cao, Wenrui Xie +10
With the tremendously increasing number of videos, there is a great demand for techniques that help people quickly navigate to the video segments they are interested in. However, c…
Revising Image-Text Retrieval via Multi-Modal Entailment
Xu Yan, Chunhui Ai, Ziqiang Cao +4
An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption match…
KE-QI: A Knowledge Enhanced Article Quality Identification Dataset
Chunhui Ai, Derui Wang, Xu Yan +3
With so many articles of varying qualities being produced every moment, it is a very urgent task to screen outstanding articles and commit them to social media. To our best knowled…
General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining
Qi Lv, Ziqiang Cao, Lei Geng +3
The lack of label data is one of the significant bottlenecks for Chinese Spelling Check (CSC). Existing researches use the method of automatic generation by exploiting unlabeled da…
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
Wenhao Wu, Wei Li, Xinyan Xiao +5
Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text.…
Incorporating Relevant Knowledge in Context Modeling and Response Generation
Yanran Li, Wenjie Li, Ziqiang Cao +1
To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge. Equipped with a knowledge base, chatbots are able to extract conversation-rela…
Faithful to the Original: Fact Aware Neural Abstractive Summarization
Ziqiang Cao, Furu Wei, Wenjie Li +1
Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly…