Picture for Jiale Cheng

Jiale Cheng

AlignBench: Benchmarking Chinese Alignment of Large Language Models

Add code
Dec 05, 2023
Viaarxiv icon

CritiqueLLM: Scaling LLM-as-Critic for Effective and Explainable Evaluation of Large Language Model Generation

Add code
Nov 30, 2023
Viaarxiv icon

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training

Add code
Nov 08, 2023
Viaarxiv icon

Safety Assessment of Chinese Large Language Models

Add code
Apr 20, 2023
Figure 1 for Safety Assessment of Chinese Large Language Models
Figure 2 for Safety Assessment of Chinese Large Language Models
Figure 3 for Safety Assessment of Chinese Large Language Models
Figure 4 for Safety Assessment of Chinese Large Language Models
Viaarxiv icon

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Add code
Feb 18, 2023
Figure 1 for Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey
Figure 2 for Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey
Figure 3 for Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey
Figure 4 for Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey
Viaarxiv icon

PAL: Persona-Augmented Emotional Support Conversation Generation

Add code
Dec 19, 2022
Figure 1 for PAL: Persona-Augmented Emotional Support Conversation Generation
Figure 2 for PAL: Persona-Augmented Emotional Support Conversation Generation
Figure 3 for PAL: Persona-Augmented Emotional Support Conversation Generation
Figure 4 for PAL: Persona-Augmented Emotional Support Conversation Generation
Viaarxiv icon

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Add code
Dec 04, 2022
Figure 1 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
Figure 2 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
Figure 3 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
Figure 4 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
Viaarxiv icon

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

Add code
Oct 16, 2021
Figure 1 for On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Figure 2 for On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Figure 3 for On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Figure 4 for On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Viaarxiv icon