Cite
Notes
Only stored in your browser.
Attribution
Nudging: Inference-time Alignment of LLMs via Guided Decoding
arXiv 2024
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
arXiv 2023
Mitigating Label Biases for In-context Learning
from 3 papers
Antoine Bosselut
Yifan Hou
Alessandro Stolfo
Guangtao Zeng
Jiaoda Li
Mrinmaya Sachan
Sameer Singh
Wangchunshu Zhou
Yasaman Razeghi
Zeming Chen