Picture for Xiaojun Wan

Xiaojun Wan

CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing

Add code
Mar 26, 2025
Viaarxiv icon

Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators

Add code
Mar 06, 2025
Viaarxiv icon

Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review

Add code
Feb 18, 2025
Viaarxiv icon

Who Writes What: Unveiling the Impact of Author Roles on AI-generated Text Detection

Add code
Feb 18, 2025
Viaarxiv icon

A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability

Add code
Feb 17, 2025
Viaarxiv icon

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference

Add code
Dec 31, 2024
Figure 1 for Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Figure 2 for Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Figure 3 for Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Figure 4 for Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Viaarxiv icon

DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models

Add code
Dec 17, 2024
Viaarxiv icon

$B^4$: A Black-Box Scrubbing Attack on LLM Watermarks

Add code
Nov 02, 2024
Viaarxiv icon

Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation

Add code
Oct 22, 2024
Figure 1 for Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
Figure 2 for Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
Figure 3 for Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
Figure 4 for Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
Viaarxiv icon

Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models

Add code
Oct 17, 2024
Figure 1 for Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
Figure 2 for Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
Figure 3 for Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
Figure 4 for Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
Viaarxiv icon