Skeleton-of-Thought

Let us accelerate the end-to-end generation of LLMs by 2x without any change to the model, system, or hardware! [ArXiv] [BibTex] [Code] This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LLMs. In this work, motivated by the thinking and writing process of humans, we propose Skeleton-of-Thought (SoT), which first guides LLMs to generate the skeleton of the answer, and then conducts parallel API calls or batched decoding to complete the contents of each skeleton point in parallel. Not only does SoT provide considerable speed-ups across 12 LLMs, but it can also potentially improve the answer quality on several question categories. SoT is an initial attempt at data-centric optimization for inference efficiency, and further underscores the potential of pushing LLMs to think more like a human for answe

Skeleton-of-Thought Search this site Embedded Files Skip to main content Skip to navigation Skeleton-of-Thought Xuefei Ning * , Zinan Lin * , Zixuan Zhou * , Zifu Wang , Huazhong Yang , Yu Wang Let us accelerate the end-to-end generation of LLMs by 2x without any change to the model, system, or hardware! [ ArXiv ] [ BibTex ] [ Code ] [ Open Review ] [ Poster ] Abstract This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LL

related reading

• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• Chain of Draft: Thinking Faster by Writing Lessarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
• 2402.07927arxiv.org
• [2402.12374] Sequoia: Scalable, Robust, and Hardware-aware Speculative Decodingarxiv.org
• Large Language Diffusion Modelsarxiv.org
• [2205.11916] Large Language Models are Zero-Shot Reasonersarxiv.org
• [2304.13343] Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory Systemarxiv.org
• [2503.18866] Reasoning to Learn from Latent Thoughtsarxiv.org
• Unlocking the Working Memory of Large Language Models for Latent Reasoningarxiv.org