Picture for Zhuang Li

Zhuang Li

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

Add code
Feb 20, 2025
Viaarxiv icon

BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks

Add code
Jan 21, 2025
Figure 1 for BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
Figure 2 for BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
Figure 3 for BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
Figure 4 for BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
Viaarxiv icon

Overview of the 2024 ALTA Shared Task: Detect Automatic AI-Generated Sentences for Human-AI Hybrid Articles

Add code
Dec 19, 2024
Viaarxiv icon

Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues

Add code
Oct 04, 2024
Figure 1 for Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Figure 2 for Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Figure 3 for Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Figure 4 for Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Viaarxiv icon

From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?

Add code
Jul 29, 2024
Figure 1 for From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Figure 2 for From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Figure 3 for From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Figure 4 for From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Viaarxiv icon

Bridging Law and Data: Augmenting Reasoning via a Semi-Structured Dataset with IRAC methodology

Add code
Jun 19, 2024
Viaarxiv icon

SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking

Add code
Jun 16, 2024
Figure 1 for SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Figure 2 for SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Figure 3 for SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Figure 4 for SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Viaarxiv icon

NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human

Add code
Jun 06, 2024
Figure 1 for NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Figure 2 for NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Figure 3 for NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Figure 4 for NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Viaarxiv icon

IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models

Add code
Apr 21, 2024
Viaarxiv icon

DragAnything: Motion Control for Anything using Entity Representation

Add code
Mar 15, 2024
Viaarxiv icon