1 code implementation • 22 Aug 2024 • Dingkang Yang, Dongling Xiao, Jinjie Wei, Mingcheng Li, Zhaoyu Chen, Ke Li, Lihua Zhang
In this paper, we propose a Comparator-driven Decoding-Time (CDT) framework to alleviate the response hallucination.
no code implementations • 14 Jun 2024 • Jiawei Chen, Dingkang Yang, Tong Wu, Yue Jiang, Xiaolu Hou, Mingcheng Li, Shunli Wang, Dongling Xiao, Ke Li, Lihua Zhang
To bridge this gap, we introduce Med-HallMark, the first benchmark specifically designed for hallucination detection and evaluation within the medical multimodal domain.
1 code implementation • 29 May 2024 • Dingkang Yang, Jinjie Wei, Dongling Xiao, Shunli Wang, Tong Wu, Gang Li, Mingcheng Li, Shuaibing Wang, Jiawei Chen, Yue Jiang, Qingyao Xu, Ke Li, Peng Zhai, Lihua Zhang
In the parameter-efficient secondary SFT phase, a mixture of universal-specific experts strategy is presented to resolve the competency conflict between medical generalist and pediatric expertise mastery.
no code implementations • 8 Mar 2024 • Dingkang Yang, Mingcheng Li, Dongling Xiao, Yang Liu, Kun Yang, Zhaoyu Chen, Yuzheng Wang, Peng Zhai, Ke Li, Lihua Zhang
In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases.
no code implementations • 11 May 2023 • Linzheng Chai, Dongling Xiao, Jian Yang, Liqun Yang, Qian-Wen Zhang, Yunbo Cao, Zhoujun Li, Zhao Yan
Context-dependent Text-to-SQL aims to translate multi-turn natural language questions into SQL queries.
no code implementations • 16 May 2022 • Dongling Xiao, Linzheng Chai, Qian-Wen Zhang, Zhao Yan, Zhoujun Li, Yunbo Cao
Context-dependent text-to-SQL is the task of translating multi-turn questions into database-related SQL queries.
2 code implementations • NAACL 2021 • Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information.
6 code implementations • 26 Jan 2020 • Dongling Xiao, Han Zhang, Yukun Li, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.
Ranked #1 on
Question Generation
on SQuAD1.1
(using extra training data)
1 code implementation • 24 Sep 2019 • Dongling Xiao, Chang Liu, Qi. Wang, Chao Wang, Xin Zhang
For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required.