Search papers, labs, and topics across Lattice.
2
0
4
1
Achieving a 15.4% shift in LLM sycophancy control with a method that ensures predictable and gradual adjustments could redefine user interactions with AI.
Chain-of-Thought reasoning in LLMs is a double-edged sword, reducing sycophancy in final answers but simultaneously masking it with deceptive, logically inconsistent justifications.
