Picture for Burcu Sayin

Burcu Sayin

Towards Reliable Retrieval in RAG Systems for Large Legal Datasets

Add code
Oct 08, 2025
Viaarxiv icon

Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?

Add code
Jan 24, 2025
Figure 1 for Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?
Figure 2 for Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?
Figure 3 for Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?
Figure 4 for Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?
Viaarxiv icon

Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain

Add code
Mar 29, 2024
Figure 1 for Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
Figure 2 for Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
Figure 3 for Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
Figure 4 for Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
Viaarxiv icon

Learning To Guide Human Decision Makers With Vision-Language Models

Add code
Mar 28, 2024
Viaarxiv icon

Rethinking and Recomputing the Value of ML Models

Add code
Sep 30, 2022
Figure 1 for Rethinking and Recomputing the Value of ML Models
Figure 2 for Rethinking and Recomputing the Value of ML Models
Figure 3 for Rethinking and Recomputing the Value of ML Models
Figure 4 for Rethinking and Recomputing the Value of ML Models
Viaarxiv icon

The Science of Rejection: A Research Area for Human Computation

Add code
Nov 11, 2021
Figure 1 for The Science of Rejection: A Research Area for Human Computation
Viaarxiv icon

Active Learning from Crowd in Document Screening

Add code
Nov 11, 2020
Figure 1 for Active Learning from Crowd in Document Screening
Figure 2 for Active Learning from Crowd in Document Screening
Figure 3 for Active Learning from Crowd in Document Screening
Viaarxiv icon