Picture for Wei Bi

Wei Bi

Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text

Add code
May 21, 2024
Viaarxiv icon

Sequence can Secretly Tell You What to Discard

Apr 24, 2024
Figure 1 for Sequence can Secretly Tell You What to Discard
Figure 2 for Sequence can Secretly Tell You What to Discard
Figure 3 for Sequence can Secretly Tell You What to Discard
Figure 4 for Sequence can Secretly Tell You What to Discard
Viaarxiv icon

DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory

Mar 04, 2024
Figure 1 for DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory
Figure 2 for DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory
Figure 3 for DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory
Figure 4 for DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory
Viaarxiv icon

FuseChat: Knowledge Fusion of Chat Models

Add code
Mar 03, 2024
Viaarxiv icon

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers

Add code
Feb 29, 2024
Viaarxiv icon

Retrieval is Accurate Generation

Add code
Feb 29, 2024
Viaarxiv icon

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models

Feb 21, 2024
Viaarxiv icon

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models

Add code
Feb 12, 2024
Viaarxiv icon

Mitigating Hallucinations of Large Language Models via Knowledge Consistent Alignment

Add code
Jan 28, 2024
Viaarxiv icon

Knowledge Fusion of Large Language Models

Add code
Jan 22, 2024
Viaarxiv icon