Xiting Wang
13 papers · 371 citations
Most-cited papers
- Uncovering Safety Risks Of Large Language Models Through Concept Activation Vector2024 · 69 citations
- From Instructions To Intrinsic Human Values -- A Survey Of Alignment Goals For Big Models2023 · 64 citations
- Value FULCRA: Mapping Large Language Models To The Multidimensional Spectrum Of Basic Human Values2023 · 53 citations
- RATT: A Thought Structure For Coherent And Correct LLM Reasoning2024 · 48 citations
Topics