When More is Less: Understanding Chain-of-Thought Length in LLMs (2025 · 73 citations)
The paper asks whether longer Chain-of-Thought (CoT) reasoning always helps LLMs. The authors argue that it does not. They combine three lines of evidence: measurements on public models, controlled experiments, and a formal model. Public models include the Qwen2.5 Instruct series on MATH Level 5, plus RL runs. The…
Bidirectional Semantic Enhancement for Schema Routing Across Large-Scale Databases (2026)
The paper tackles schema routing: picking the few relevant tables from repositories that may hold thousands of them before an LLM writes SQL.
KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning (2026)
General-purpose LLMs often reason poorly about chemical reactions. They mislabel functional groups, mix up reaction classes and propose products with atoms that have no source in the reactants. Existing benchmarks mostly test product generation or fact recall, not mechanistic understanding. The authors address both…

Co-authors here

5 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 68 times (of the 149,439 papers whose bibliographies we read); 24 citing papers with a page here →.

Updated 2 November 2026