Profiles2024-2026
Youliang Yuan
The Chinese University of Hong Kong
11Papers
0Last author
20Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- Curing Miracle Steps in LLM Mathematical Reasoning with Rubric RewardsAuthor 1 of 10ACL 2026 · 5 citations
- Identifying the Achilles' Heel: An Iterative Method for Uncovering Factual Errors in Large Language ModelsAuthor 5 of 10ACL Findings 2026
- Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal TrainingAuthor 1 of 8ACL 2025 · 65 citations
- Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMsAuthor 3 of 7ACL 2025 · 20 citations
- ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool InvocationsAuthor 2 of 6EMNLP 2025 · 7 citations
- Learning to Ask: When LLM Agents Meet Unclear InstructionAuthor 7 of 10EMNLP 2025 · 1 citation
- GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherAuthor 1 of 7ICLR 2024 · 441 citations
- On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMsAuthor 6 of 9ICLR 2024 · 85 citations
- All Languages Matter: On the Multilingual Safety of LLMsAuthor 4 of 7ACL Findings 2024 · 21 citations
- LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language ModelsAuthor 4 of 8EMNLP 2024 · 10 citations
- Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMsAuthor 2 of 4EMNLP Findings 2024 · 1 citation
