Picture for A-Long Jin

A-Long Jin

TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions

Add code
Oct 05, 2024
Figure 1 for TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
Figure 2 for TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
Figure 3 for TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
Figure 4 for TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
Viaarxiv icon

Improving Factual Error Correction by Learning to Inject Factual Errors

Add code
Dec 12, 2023
Viaarxiv icon

AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators

Add code
Mar 29, 2023
Viaarxiv icon

Curriculum Sampling for Dense Retrieval with Document Expansion

Add code
Dec 18, 2022
Viaarxiv icon