Picture for Jiaxin Wen

Jiaxin Wen

Unsupervised Elicitation of Language Models

Add code
Jun 11, 2025
Viaarxiv icon

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Add code
Nov 26, 2024
Figure 1 for Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Figure 2 for Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Figure 3 for Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Figure 4 for Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Viaarxiv icon

Learning Task Decomposition to Assist Humans in Competitive Programming

Add code
Jun 07, 2024
Figure 1 for Learning Task Decomposition to Assist Humans in Competitive Programming
Figure 2 for Learning Task Decomposition to Assist Humans in Competitive Programming
Figure 3 for Learning Task Decomposition to Assist Humans in Competitive Programming
Figure 4 for Learning Task Decomposition to Assist Humans in Competitive Programming
Viaarxiv icon

Unveiling the Implicit Toxicity in Large Language Models

Add code
Nov 29, 2023
Viaarxiv icon

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

Add code
Jul 10, 2023
Figure 1 for Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
Figure 2 for Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
Figure 3 for Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
Figure 4 for Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
Viaarxiv icon

Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training

Add code
May 04, 2023
Figure 1 for Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
Figure 2 for Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
Figure 3 for Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
Figure 4 for Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
Viaarxiv icon

AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning

Add code
Nov 29, 2022
Viaarxiv icon

Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China

Add code
Sep 21, 2022
Figure 1 for Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China
Figure 2 for Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China
Figure 3 for Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China
Figure 4 for Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China
Viaarxiv icon

Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation

Add code
Apr 22, 2022
Figure 1 for Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
Figure 2 for Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
Figure 3 for Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
Figure 4 for Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
Viaarxiv icon

EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training

Add code
Mar 17, 2022
Figure 1 for EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Figure 2 for EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Figure 3 for EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Figure 4 for EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Viaarxiv icon