Search Results for author: Xiaodong Yu

Found 17 papers, 7 papers with code

Capturing the Content of a Document through Complex Event Identification

no code implementations *SEM (NAACL) 2022 Zheng Qi, Elior Sulem, Haoyu Wang, Xiaodong Yu, Dan Roth

We address this task as a pipeline, first predicting whether two granular events mentioned in the text belong to the same complex event, independently of their position in the text, and then using this to cluster them into complex events.

Representation Learning

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity

no code implementations5 Jun 2024 Wentao Guo, Jikai Long, Yimeng Zeng, Zirui Liu, Xinyu Yang, Yide Ran, Jacob R. Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen, Zhaozhuo Xu

Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes.


Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents

no code implementations8 May 2024 Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee

We propose KNN-former, which incorporates a new kind of spatial bias in attention calculation based on the K-nearest-neighbor (KNN) graph of document entities.

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks

no code implementations19 Oct 2023 Xiaodong Yu, Hao Cheng, Xiaodong Liu, Dan Roth, Jianfeng Gao

Specifically, given the potential of data contamination (e. g., leading to memorization), good static benchmark performance does not ensure that model can reliably use the provided evidence for responding, which is essential to avoid hallucination when the required knowledge is new or private.

Hallucination Hallucination Evaluation +6

Benchmarking and In-depth Performance Study of Large Language Models on Habana Gaudi Processors

no code implementations29 Sep 2023 Chengming Zhang, Baixi Sun, Xiaodong Yu, Zhen Xie, Weijian Zheng, Kamil Iskra, Pete Beckman, Dingwen Tao

Thirdly, we evaluate the performance of Transformers on GAUDI, particularly in handling long sequences and uncovering performance bottlenecks.

Benchmarking Computational Efficiency

Building Interpretable and Reliable Open Information Retriever for New Domains Overnight

no code implementations9 Aug 2023 Xiaodong Yu, Ben Zhou, Dan Roth

Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA).

Information Retrieval Open-Domain Question Answering +3

SOLAR: A Highly Optimized Data Loading Framework for Distributed Training of CNN-based Scientific Surrogates

no code implementations1 Nov 2022 Baixi Sun, Xiaodong Yu, Chengming Zhang, Jiannan Tian, Sian Jin, Kamil Iskra, Tao Zhou, Tekin Bicer, Pete Beckman, Dingwen Tao

Our evaluation with three scientific surrogates and 32 GPUs illustrates that SOLAR can achieve up to 24. 4X speedup over PyTorch Data Loader and 3. 52X speedup over state-of-the-art data loaders.


Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts

no code implementations30 Oct 2022 Ben Zhou, Kyle Richardson, Xiaodong Yu, Dan Roth

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems.

Language Modelling Semantic Parsing +1

SOIT: Segmenting Objects with Instance-Aware Transformers

1 code implementation21 Dec 2021 Xiaodong Yu, Dahu Shi, Xing Wei, Ye Ren, Tingqun Ye, Wenming Tan

The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer.

Instance Segmentation Segmentation +1

Event Linking: Grounding Event Mentions to Wikipedia

1 code implementation15 Dec 2021 Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth

Third, we retrain and evaluate two state-of-the-art (SOTA) entity linking models, showing the challenges of event linking, and we propose an event-specific linking system EVELINK to set a competitive result for the new task.

Entity Linking Natural Language Understanding

Design Challenges in Low-resource Cross-lingual Entity Linking

1 code implementation EMNLP 2020 Xingyu Fu, Weijia Shi, Xiaodong Yu, Zian Zhao, Dan Roth

Cross-lingual Entity Linking (XEL), the problem of grounding mentions of entities in a foreign language text into an English knowledge base such as Wikipedia, has seen a lot of research in recent years, with a range of promising techniques.

Cross-Lingual Entity Linking Entity Linking

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