Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang +1 more
2/12/2026

No official code found. Best implementation: imagination-research/sot (184 stars, MIT, last commit 2024-03-01).

Semantic Scholar

Code Implementations(1)

imagination-research/sotCommunity62%
MIT

[ICLR 2024] Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

18417Shell, PythonOct 8, 20232 years agoMIT

Similar Papers

UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation

97% match1 repo92026

TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

97% match1 repo232026

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval

96% match2026

TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection

96% match1 repo52026

SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization

95% match2026

CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering

93% match2026

Cite this paper

@article{ning2026skeletonofthought,
  title  = {Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation},
  author = {Xuefei Ning and Zinan Lin and Zixuan Zhou and Zifu Wang and Huazhong Yang and Yu Wang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:37686e751ab08c848300d4868b6ed933e53c4530},
  journal = {ICLR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/37686e751ab08c848300d4868b6ed933e53c4530.svg)](https://codeofpaper.com/paper/37686e751ab08c848300d4868b6ed933e53c4530)

Discussion