Search Results for author: Xifeng Yan

Found 40 papers, 20 papers with code

Do you really follow me? Adversarial Instructions for Evaluating the Robustness of Large Language Models

no code implementations17 Aug 2023 Zekun Li, Baolin Peng, Pengcheng He, Xifeng Yan

The objective of this benchmark is to quantify the extent to which LLMs are influenced by injected adversarial instructions and assess their ability to differentiate between these adversarial instructions and original user instructions.

Instruction Following

Augmenting Language Models with Long-Term Memory

1 code implementation12 Jun 2023 Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, Furu Wei

Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness.

Language Modelling Retrieval

STEPS: A Benchmark for Order Reasoning in Sequential Tasks

no code implementations7 Jun 2023 Weizhi Wang, Hong Wang, Xifeng Yan

Therefore, to verify the order reasoning capability of current neural models in sequential tasks, we propose a challenging benchmark , named STEPS.

Graph Reasoning for Question Answering with Triplet Retrieval

no code implementations30 May 2023 Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng Yan, Chao Zhang, Bing Yin

State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e. g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering.

Knowledge Graphs Question Answering +1

Bot or Human? Detecting ChatGPT Imposters with A Single Question

1 code implementation10 May 2023 Hong Wang, Xuan Luo, Weizhi Wang, Xifeng Yan

Large language models like ChatGPT have recently demonstrated impressive capabilities in natural language understanding and generation, enabling various applications including translation, essay writing, and chit-chatting.

Language Modelling Large Language Model +2

Time Series as Images: Vision Transformer for Irregularly Sampled Time Series

1 code implementation1 Mar 2023 Zekun Li, Shiyang Li, Xifeng Yan

This paper studies the problem from a whole new perspective: transforming irregularly sampled time series into line graph images and adapting powerful vision transformers to perform time series classification in the same way as image classification.

Image Classification Time Series +1

Guiding Large Language Models via Directional Stimulus Prompting

1 code implementation22 Feb 2023 Zekun Li, Baolin Peng, Pengcheng He, Michel Galley, Jianfeng Gao, Xifeng Yan

The directional stimulus serves as hints or cues for each input query to guide LLMs toward the desired output, such as keywords that the desired summary should include for summarization.

Avg Language Modelling +2

Language Model Detoxification in Dialogue with Contextualized Stance Control

no code implementations25 Jan 2023 Jing Qian, Xifeng Yan

To reduce the toxic degeneration in a pretrained Language Model (LM), previous work on Language Model detoxification has focused on reducing the toxicity of the generation itself (self-toxicity) without consideration of the context.

Language Modelling Response Generation

Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling

1 code implementation18 Oct 2022 Xinlu Zhang, Shiyang Li, Zhiyu Chen, Xifeng Yan, Linda Petzold

Our method first addresses irregularity in each single modality by (1) modeling irregular time series by dynamically incorporating hand-crafted imputation embeddings into learned interpolation embeddings via a gating mechanism, and (2) casting a series of clinical note representations as multivariate irregular time series and tackling irregularity via a time attention mechanism.

Imputation Irregular Time Series +2

Explanations from Large Language Models Make Small Reasoners Better

no code implementations13 Oct 2022 Shiyang Li, Jianshu Chen, Yelong Shen, Zhiyu Chen, Xinlu Zhang, Zekun Li, Hong Wang, Jing Qian, Baolin Peng, Yi Mao, Wenhu Chen, Xifeng Yan

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations.

Explanation Generation Multi-Task Learning

Controllable Dialogue Simulation with In-Context Learning

1 code implementation9 Oct 2022 Zekun Li, Wenhu Chen, Shiyang Li, Hong Wang, Jing Qian, Xifeng Yan

Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed.

Data Augmentation Language Modelling +1

Limitations of Language Models in Arithmetic and Symbolic Induction

no code implementations9 Aug 2022 Jing Qian, Hong Wang, Zekun Li, Shiyang Li, Xifeng Yan

LMs with tutor is able to deliver 100% accuracy in situations of OOD and repeating symbols, shedding new insights on the boundary of large LMs in induction.

Visually-Augmented Language Modeling

1 code implementation20 May 2022 Weizhi Wang, Li Dong, Hao Cheng, Haoyu Song, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, Furu Wei

With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling by attending to both text context and visual knowledge in images.

Image Retrieval Language Modelling +1

Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding

no code implementations Findings (EMNLP) 2021 Shiyang Li, Semih Yavuz, Wenhu Chen, Xifeng Yan

Task-adaptive pre-training (TAPT) and Self-training (ST) have emerged as the major semi-supervised approaches to improve natural language understanding (NLU) tasks with massive amount of unlabeled data.

named-entity-recognition Named Entity Recognition +6

Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation

no code implementations14 Jul 2021 Ning Ma, Jiajun Bu, Lixian Lu, Jun Wen, Zhen Zhang, Sheng Zhou, Xifeng Yan

Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc.

Source-Free Domain Adaptation

Inductive Relation Prediction by BERT

1 code implementation12 Mar 2021 Hanwen Zha, Zhiyu Chen, Xifeng Yan

Relation prediction in knowledge graphs is dominated by embedding based methods which mainly focus on the transductive setting.

Few-Shot Learning Inductive Relation Prediction +3

Composite Re-Ranking for Efficient Document Search with BERT

no code implementations11 Mar 2021 Yingrui Yang, Yifan Qiao, Jinjin Shao, Mayuresh Anand, Xifeng Yan, Tao Yang

By applying token encoding on top of a dual-encoder architecture, BECR separates the attentions between a query and a document while capturing the contextual semantics of a query.


Cross-modal Image Retrieval with Deep Mutual Information Maximization

no code implementations10 Mar 2021 Chunbin Gu, Jiajun Bu, Xixi Zhou, Chengwei Yao, Dongfang Ma, Zhi Yu, Xifeng Yan

Prior work usually uses a three-stage strategy to tackle this task: 1) extract the features of the inputs; 2) fuse the feature of the source image and its modified text to obtain fusion feature; 3) learn a similarity metric between the desired image and the source image + modified text by using deep metric learning.

Cross-Modal Retrieval Image Retrieval +3

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

1 code implementation16 Nov 2020 Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, Yu Su

To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64, 331 questions, GrailQA, and provide evaluation settings for all three levels of generalization.

Knowledge Base Question Answering

Inter-Series Attention Model for COVID-19 Forecasting

1 code implementation25 Oct 2020 Xiaoyong Jin, Yu-Xiang Wang, Xifeng Yan

COVID-19 pandemic has an unprecedented impact all over the world since early 2020.

Time Series Time Series Analysis

CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

2 code implementations ICLR 2021 Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong

Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.

Ranked #2 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)

Dialogue State Tracking Multi-domain Dialogue State Tracking

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

1 code implementation EMNLP 2020 Wenhu Chen, Yu Su, Xifeng Yan, William Yang Wang

We propose a knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text.

General Knowledge KG-to-Text Generation +1

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

1 code implementation31 Oct 2019 Arvind Neelakantan, Semih Yavuz, Sharan Narang, Vishaal Prasad, Ben Goodrich, Daniel Duckworth, Chinnadhurai Sankar, Xifeng Yan

In this paper, we develop Neural Assistant: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output.

Response Generation Retrieval +1

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

2 code implementations NeurIPS 2019 Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, Xifeng Yan

Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation.

Ranked #27 on Image Generation on ImageNet 64x64 (Bits per dim metric)

Time Series Time Series Forecasting

Global Textual Relation Embedding for Relational Understanding

1 code implementation ACL 2019 Zhiyu Chen, Hanwen Zha, Honglei Liu, Wenhu Chen, Xifeng Yan, Yu Su

Pre-trained embeddings such as word embeddings and sentence embeddings are fundamental tools facilitating a wide range of downstream NLP tasks.

Action Classification Sentence Embeddings +1

What It Takes to Achieve 100\% Condition Accuracy on WikiSQL

no code implementations EMNLP 2018 Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan

The SQL queries in WikiSQL are simple: Each involves one relation and does not have any join operation.


XL-NBT: A Cross-lingual Neural Belief Tracking Framework

1 code implementation EMNLP 2018 Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan, William Yang Wang

Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data.

Transfer Learning

DialSQL: Dialogue Based Structured Query Generation

no code implementations ACL 2018 Izzeddin Gur, Semih Yavuz, Yu Su, Xifeng Yan

The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries.

Semantic Parsing Translation

Variational Knowledge Graph Reasoning

no code implementations NAACL 2018 Wenhu Chen, Wenhan Xiong, Xifeng Yan, William Wang

Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community.

Knowledge Graphs Link Prediction +1

Recovering Question Answering Errors via Query Revision

no code implementations EMNLP 2017 Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan

The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes.

Question Answering Semantic Parsing

Behavior Query Discovery in System-Generated Temporal Graphs

no code implementations18 Nov 2015 Bo Zong, Xusheng Xiao, Zhichun Li, Zhen-Yu Wu, Zhiyun Qian, Xifeng Yan, Ambuj K. Singh, Guofei Jiang

In this work, we investigate how to query temporal graphs and treat query formulation as a discriminative temporal graph pattern mining problem.

Cannot find the paper you are looking for? You can Submit a new open access paper.