activity
20162023
most citedSiren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

244 citations · 991 across the 40 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.CV2021

Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification

Yang Liu, Weifeng Zhang, Chao Xiang +3

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-da…

cs.CL2021★ 3 cited

Assessing Dialogue Systems with Distribution Distances

Jiannan Xiang, Yahui Liu, Deng Cai +3

An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems. Existing automatic evaluation metrics are based on turn-leve…

cs.CL2021★ 5 cited

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering

Weiwen Xu, Huihui Zhang, Deng Cai +1

Knowledge retrieval and reasoning are two key stages in multi-hop question answering (QA) at web scale. Existing approaches suffer from low confidence when retrieving evidence fact…

cs.CV2021★ 28 cited

ES-Net: Erasing Salient Parts to Learn More in Re-Identification

Dong Shen, Shuai Zhao, Jinming Hu +3

As an instance-level recognition problem, re-identification (re-ID) requires models to capture diverse features. However, with continuous training, re-ID models pay more and more a…

cs.CL2021★ 10 cited

Non-Autoregressive Text Generation with Pre-trained Language Models

Yixuan Su, Deng Cai, Yan Wang +4

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…

cs.CV2021★ 87 cited

Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification

Hao Feng, Minghao Chen, Jinming Hu +3

In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic perf…