A5047817212- Topic Modeling
- Natural Language Processing Techniques
- Rough Sets and Fuzzy Logic
- Advanced Chemical Sensor Technologies
- Olfactory and Sensory Function Studies
- Conducting polymers and applications
- Text and Document Classification Technologies
- Speech and dialogue systems
- Emotion and Mood Recognition
- Advanced Computational Techniques and Applications
- Image Processing and 3D Reconstruction
- Authorship Attribution and Profiling
Tsinghua University
2025
Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic discourse. Existing literature neglects the origin evolution of LLM personalities, as well effective personality control. To fill these gaps, our study embarked on a comprehensive investigation into We investigated several typical methods to influence LLMs,...
Multimodal large language models (MLLMs) have achieved significant advancements in integrating visual and linguistic understanding. While existing benchmarks evaluate these context-rich, real-life scenarios, they often overlook fundamental perceptual skills essential for environments deviating from everyday realism. In particular, geometric perception, the ability to interpret spatial relationships abstract patterns, remains underexplored. To address this limitation, we introduce GePBench, a...