2 papers
cs.IR2026
Query Expansion Is More Than Generation: Improving Dense Retrieval through Better Integration
Siyuan Sun, Mihai Surdeanu
Large language models (LLMs) can generate query expansions without task-specific training, yet the same expansions often make a frozen dense retriever worse. We identify an underex…
cs.AI2026
Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment
Jing Shao, Qifeng Wu, Hanyu Zhang +2
Large language model (LLM)-based Socratic tutors increasingly guide students through multi-turn questioning, but they can suffer from scaffolding collapse: under sustained student…