conftrace_

Liu Yan

6 papers · 2024–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

EMNLP (3) ACL (2) ICLR (1)

Top co-authors

Han Qiu (6) Tianwei Zhang (4) Minlie Huang (3) Qingjie Zhang (3) Di Wang (3) Ke Xu (3) Chao Zhang (3) Haiqin Weng (2) Jianshuo Dong (2) Yiming Li (2)

Research topics

Artificial Intelligence (6) Core AI (6) Machine Learning (2) Deep Learning (1) Natural Language Processing (1) Security & Privacy (1) Application Areas (1) Applications (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

large language model (4) data augmentation (1) prompt engineering (1) instruction following (1) intent detection (1) harmful content (1) safety alignment (1) hidden state (1) synthetic data (1) jailbreak attack (1) information leakage (1) safety benchmark (1) linear probing (1) cognitive bia (1) training data (1) token analysis (1) model internal (1) chinese language (1) prompt bia (1) probing classifier (1)

Papers

Revisiting the Reliability of Language Models in Instruction-Following ACL 2026 A Benchmark for Semantic Sensitive Information in LLMs Outputs ICLR 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Speculating LLMs’ Chinese Training Data Pollution from Their Tokens EMNLP 2025 Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024