Papers by Youliang Yu

2 papers
Imbalanced Gradients in RL Post-Training of Multi-Task LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Large-gradient tasks can achieve similar or even much lower learning gains than small-grading ones.
Approach: They show that large-gradient tasks can achieve lower learning gains than small-grading ones . large-grade tasks can accomplish similar or even lower learning gain than small grade ones if they are large .
Outcome: The proposed approach fails when certain tasks produce larger gradients . Large-gradient tasks can achieve lower learning gains than small-gradent ones .
SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing educational LLMs are vulnerable to pedagogical jailbreaks where students use answer-inducing prompts to elicit solutions rather than scaffolded instructions.
Approach: They propose a graph-augmented tutoring pipeline that infers prerequisite concepts from queries and identifies mastery gaps.
Outcome: The proposed method improves safety under two pedagogical jailbreak scenarios while maintaining near-ceiling helpfulness under the same evaluation protocol.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations