Suchergebnisse - Lin, Victoria

Optimizing Language Models for Human Preferences is a Causal Inference Problem von Lin, Victoria, Ben-Michael, Eli, Morency, Louis-Philippe

Volltext

Isolated Causal Effects of Natural Language von Lin, Victoria, Morency, Louis-Philippe, Ben-Michael, Eli

Volltext

Omitted Variable Bias in Language Models Under Distribution Shift von Lin, Victoria, Morency, Louis-Philippe, Ben-Michael, Eli

Volltext

Stage-wise Fine-tuning for Graph-to-Text Generation von Wang, Qingyun, Yavuz, Semih, Lin, Victoria, Ji, Heng, Rajani, Nazneen

Volltext

Sirius: Contextual Sparsity with Correction for Efficient LLMs von Zhou, Yang, Chen, Zhuoming, Xu, Zhaozhuo, Lin, Victoria, Chen, Beidi

Volltext

The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study von Lin, Victoria, Yun, Taedong, Matarić, Maja, Canny, John, Gretton, Arthur, D'Amour, Alexander

Volltext

Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency von Lin, Victoria, Xu, Xinnuo, Lawrence, Rachel, Ueno, Risa, Sharma, Amit, Gonzalez, Javier, Prasad, Niranjani

Volltext