Xing Han Lu's picture

Xing Han Lu

xhluca

·

https://xinghanlu.com

xhluca

xhluca

AI & ML interests

None yet

Articles

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

Organizations

xhluca's activity

upvoted a paper about 1 month ago

Interpretability Needs a New Paradigm

Paper • 2405.05386 • Published May 8 • 3

upvoted a paper 3 months ago

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Paper • 2404.05961 • Published Apr 9 • 62

upvoted a collection 3 months ago

LLM2Vec

13 items • Updated about 23 hours ago • 19

upvoted a paper 3 months ago

Improving Text-to-Image Consistency via Automatic Prompt Optimization

Paper • 2403.17804 • Published Mar 26 • 14

upvoted 2 collections 5 months ago

WebLINX Models

https://mcgill-nlp.github.io/weblinx • 17 items • Updated about 23 hours ago • 6

WebLINX

https://mcgill-nlp.github.io/weblinx • 10 items • Updated about 23 hours ago • 4

upvoted 10 papers 5 months ago

Improving Automatic VQA Evaluation Using Large Language Models

Paper • 2310.02567 • Published Oct 4, 2023 • 3

MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting

Paper • 2210.07179 • Published Oct 13, 2022 • 3

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval

Paper • 2104.08801 • Published Apr 18, 2021 • 1

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Paper • 2402.05930 • Published Feb 8 • 35

Image Retrieval from Contextual Descriptions

Paper • 2203.15867 • Published Mar 29, 2022 • 1

Using In-Context Learning to Improve Dialogue Safety

Paper • 2302.00871 • Published Feb 2, 2023 • 1

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages

Paper • 2211.14402 • Published Nov 25, 2022 • 1

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Paper • 2212.09146 • Published Dec 18, 2022 • 3

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering

Paper • 2307.16877 • Published Jul 31, 2023 • 3

Can Large Language Models Explain Themselves?

Paper • 2401.07927 • Published Jan 15 • 4

upvoted 2 collections 5 months ago

MLQuestions

5 items • Updated about 23 hours ago • 1

FaithDial

3 items • Updated about 23 hours ago • 1

upvoted a collection 6 months ago

Statcan Dialogue Dataset & Models

mcgill-nlp.github.io/statcan-dialogue-dataset • 18 items • Updated about 23 hours ago • 2

upvoted a paper 10 months ago

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue

Paper • 2204.10757 • Published Apr 22, 2022 • 1

upvoted 2 papers about 1 year ago

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents

Paper • 2304.01412 • Published Apr 3, 2023 • 1

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

Paper • 2204.03025 • Published Apr 6, 2022 • 2