← Search

Zinan Ling

2 accepted papers

2026

Weak-to-Strong Generalization with Failure Trajectories

ICLR 2026poster

Weak-to-Strong generalization (W2SG) is a new trend to elicit the full capabilities of a strong model with supervision from a weak model. While existing W2SG studies focus on simple tasks like binary classification, we extend this paradigm to complex interactive decision-making environments. Speci…

Cited by 0SourcecodeScholar
2026

Your Language Model Secretly Contains Personality Subnetworks

ICLR 2026poster

Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior through external knowledge such as prompting, retrieval-augmen…

Cited by 0SourcecodeScholar