Picture for Hongyuan Lu

Hongyuan Lu

Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models

Add code
Nov 02, 2024
Viaarxiv icon

Clean Evaluations on Contaminated Visual Language Models

Add code
Oct 09, 2024
Figure 1 for Clean Evaluations on Contaminated Visual Language Models
Figure 2 for Clean Evaluations on Contaminated Visual Language Models
Figure 3 for Clean Evaluations on Contaminated Visual Language Models
Figure 4 for Clean Evaluations on Contaminated Visual Language Models
Viaarxiv icon

Toxic Subword Pruning for Dialogue Response Generation on Large Language Models

Add code
Oct 05, 2024
Viaarxiv icon

Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations

Add code
Jul 04, 2024
Figure 1 for Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Figure 2 for Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Figure 3 for Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Figure 4 for Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Viaarxiv icon

Unveiling the Generalization Power of Fine-Tuned Large Language Models

Add code
Mar 14, 2024
Figure 1 for Unveiling the Generalization Power of Fine-Tuned Large Language Models
Figure 2 for Unveiling the Generalization Power of Fine-Tuned Large Language Models
Figure 3 for Unveiling the Generalization Power of Fine-Tuned Large Language Models
Figure 4 for Unveiling the Generalization Power of Fine-Tuned Large Language Models
Viaarxiv icon

Consecutive Model Editing with Batch alongside HooK Layers

Add code
Mar 08, 2024
Viaarxiv icon

CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models

Add code
Nov 15, 2023
Figure 1 for CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
Figure 2 for CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
Figure 3 for CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
Figure 4 for CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
Viaarxiv icon

TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration

Add code
Sep 28, 2023
Viaarxiv icon

EPA: Easy Prompt Augmentation on Large Language Models via Multiple Sources and Multiple Targets

Add code
Sep 09, 2023
Viaarxiv icon

Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing

Add code
May 24, 2023
Viaarxiv icon