12 citations · 33 across the 14 of their papers we have counts for
14 papers
Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
Dongfang Li, Baotian Hu, Qingcai Chen +1
Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI…
A Survey of Large Language Models Attribution
Dongfang Li, Zetian Sun, Xinshuo Hu +5
Open-domain generative systems have gained significant attention in the field of conversational AI (e.g., generative search engines). This paper presents a comprehensive review of…
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
Nengzheng Jin, Dongfang Li, Junying Chen +2
Open-domain table question answering aims to provide answers to a question by retrieving and extracting information from a large collection of tables. Existing studies of open-doma…
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
Xinshuo Hu, Dongfang Li, Baotian Hu +3
Large language models (LLMs) have been widely used in various applications but are known to suffer from issues related to untruthfulness and toxicity. While parameter-efficient mod…
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination
Dongfang Li, Jindi Yu, Baotian Hu +2
As ChatGPT and GPT-4 spearhead the development of Large Language Models (LLMs), more researchers are investigating their performance across various tasks. But more research needs t…
SeDR: Segment Representation Learning for Long Documents Dense Retrieval
Junying Chen, Qingcai Chen, Dongfang Li +1
Recently, Dense Retrieval (DR) has become a promising solution to document retrieval, where document representations are used to perform effective and efficient semantic search. Ho…
Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates
Dongfang Li, Baotian Hu, Qingcai Chen
Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explana…
Prompt-based Text Entailment for Low-Resource Named Entity Recognition
Dongfang Li, Baotian Hu, Qingcai Chen
Pre-trained Language Models (PLMs) have been applied in NLP tasks and achieve promising results. Nevertheless, the fine-tuning procedure needs labeled data of the target domain, ma…
A Survey on Table Question Answering: Recent Advances
Nengzheng Jin, Joanna Siebert, Dongfang Li +1
Table Question Answering (Table QA) refers to providing precise answers from tables to answer a user's question. In recent years, there have been a lot of works on table QA, but th…
Diaformer: Automatic Diagnosis via Symptoms Sequence Generation
Junying Chen, Dongfang Li, Qingcai Chen +2
Automatic diagnosis has attracted increasing attention but remains challenging due to multi-step reasoning. Recent works usually address it by reinforcement learning methods. Howev…
Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction
Dongfang Li, Baotian Hu, Qingcai Chen +3
Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of tw…
You Can Do Better! If You Elaborate the Reason When Making Prediction
Dongfang Li, Jingcong Tao, Qingcai Chen +1
Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack…
Semi-supervised Visual Feature Integration for Pre-trained Language Models
Lisai Zhang, Qingcai Chen, Dongfang Li +1
Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and…
BERTSel: Answer Selection with Pre-trained Models
Dongfang Li, Yifei Yu, Qingcai Chen +1
Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related ta…