Picture for Weixuan Wang

Weixuan Wang

Demystifying Multilingual Chain-of-Thought in Process Reward Modeling

Add code
Feb 18, 2025
Viaarxiv icon

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models

Add code
Jan 19, 2025
Viaarxiv icon

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors

Add code
Oct 16, 2024
Viaarxiv icon

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention

Add code
Oct 16, 2024
Figure 1 for Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Figure 2 for Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Figure 3 for Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Figure 4 for Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Viaarxiv icon

Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs

Add code
Jun 13, 2024
Figure 1 for Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
Figure 2 for Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
Figure 3 for Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
Figure 4 for Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
Viaarxiv icon

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

Add code
Jan 28, 2024
Figure 1 for Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
Figure 2 for Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
Figure 3 for Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
Figure 4 for Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
Viaarxiv icon

Retrieval-augmented Multilingual Knowledge Editing

Add code
Dec 20, 2023
Figure 1 for Retrieval-augmented Multilingual Knowledge Editing
Figure 2 for Retrieval-augmented Multilingual Knowledge Editing
Figure 3 for Retrieval-augmented Multilingual Knowledge Editing
Figure 4 for Retrieval-augmented Multilingual Knowledge Editing
Viaarxiv icon

Assessing the Reliability of Large Language Model Knowledge

Add code
Oct 15, 2023
Viaarxiv icon

Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications

Add code
Oct 11, 2023
Figure 1 for Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
Figure 2 for Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
Figure 3 for Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
Figure 4 for Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
Viaarxiv icon

Evaluating the Efficacy of Length-Controllable Machine Translation

Add code
May 03, 2023
Viaarxiv icon