Picture for Xinyu Ma

Xinyu Ma

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval

Add code
Oct 14, 2024
Figure 1 for MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
Figure 2 for MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
Figure 3 for MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
Figure 4 for MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
Viaarxiv icon

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning

Add code
Oct 14, 2024
Viaarxiv icon

JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework

Add code
Oct 11, 2024
Figure 1 for JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Figure 2 for JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Figure 3 for JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Figure 4 for JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Viaarxiv icon

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing

Add code
Jun 17, 2024
Viaarxiv icon

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset

Add code
Apr 29, 2024
Viaarxiv icon

LoRA Dropout as a Sparsity Regularizer for Overfitting Control

Add code
Apr 15, 2024
Figure 1 for LoRA Dropout as a Sparsity Regularizer for Overfitting Control
Figure 2 for LoRA Dropout as a Sparsity Regularizer for Overfitting Control
Figure 3 for LoRA Dropout as a Sparsity Regularizer for Overfitting Control
Figure 4 for LoRA Dropout as a Sparsity Regularizer for Overfitting Control
Viaarxiv icon

Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation

Add code
Apr 05, 2024
Viaarxiv icon

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

Add code
Feb 18, 2024
Viaarxiv icon

Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix

Add code
Dec 05, 2023
Viaarxiv icon

Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers

Add code
Nov 02, 2023
Viaarxiv icon