Picture for Min-Yen Kan

Min-Yen Kan

Columbia University

Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models

Add code
Dec 08, 2024
Viaarxiv icon

Reasoning Robustness of LLMs to Adversarial Typographical Errors

Add code
Nov 08, 2024
Figure 1 for Reasoning Robustness of LLMs to Adversarial Typographical Errors
Figure 2 for Reasoning Robustness of LLMs to Adversarial Typographical Errors
Figure 3 for Reasoning Robustness of LLMs to Adversarial Typographical Errors
Figure 4 for Reasoning Robustness of LLMs to Adversarial Typographical Errors
Viaarxiv icon

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization

Add code
Nov 05, 2024
Figure 1 for V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Figure 2 for V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Figure 3 for V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Figure 4 for V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Viaarxiv icon

Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models

Add code
Nov 01, 2024
Viaarxiv icon

DataTales: A Benchmark for Real-World Intelligent Data Narration

Add code
Oct 23, 2024
Viaarxiv icon

CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization

Add code
Oct 16, 2024
Viaarxiv icon

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement

Add code
Oct 12, 2024
Viaarxiv icon

MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?

Add code
Oct 06, 2024
Figure 1 for MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?
Figure 2 for MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?
Figure 3 for MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?
Figure 4 for MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?
Viaarxiv icon

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning

Add code
Sep 18, 2024
Figure 1 for TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
Figure 2 for TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
Figure 3 for TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
Figure 4 for TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
Viaarxiv icon

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs

Add code
Aug 16, 2024
Viaarxiv icon