Cite
Notes
Only stored in your browser.
Attribution
LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
arXiv 2026
Robust Multi-Objective Controlled Decoding of Large Language Models
arXiv 2025
from 2 papers
Chris Russell
Ilija Bogunovic
Sangwoong Yoon
Seongho Son
Shyam Sundhar Ramesh
Thomas Foster
William Lugoloobi
Xiaohang Tang