ThinkSwitcher: When to Think Hard, When to Think Fast
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5185-5201
Abstract
Guosheng Liang, Longguang Zhong, Ziyi Yang, Xiaojun Quan. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- C3oT: Generating Shorter Chain-of-Thought Without Compromising EffectivenessProceedings of the AAAI Conference on Artificial Intelligence, 2025
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs2025
- DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models2025
- Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference2025
- The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models2024
- Maps of Bounded Rationality: Psychology for Behavioral EconomicsAmerican Economic Review, 2003