Papers by Shaojie Zhang

2 papers
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching (2026.acl-long)

Copied to clipboard

Challenge: Existing routing methods rely on direct mapping from queries to models based on surface-level features, leading to poor generalizability on out-of-distribution data.
Approach: They propose a new routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs.
Outcome: The proposed framework improves matching accuracy while lowering inference costs . it decouples linguistic surface forms from task-intrinsic requirements .
From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Recent studies reveal large language models lack logical reasoning abilities . logical relationship understanding is a core capability underlying genuine logical thinking .
Approach: They propose a lightweight training framework targeting logical relationship understanding . they propose logical relation understanding framework that provides explicit supervision .
Outcome: The proposed framework outperforms CoT-SFT training frameworks in logical relationship understanding tasks.

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