# CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality

arXiv: https://arxiv.org/abs/2502.08923 · HTML: https://mlsanity.com/paper/2502.08923/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 34)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Repeat After Me: Transformers are Better than State Space Models at Copying](https://mlsanity.com/paper/2402.01032/) (2024)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021)
- [SPEED: Speculative Pipelined Execution for Efficient Decoding](https://mlsanity.com/paper/2310.12072/) (2023)
- [Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling](https://mlsanity.com/paper/2408.08696/) (2024)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding](https://mlsanity.com/paper/2307.05908/) (2023)
- [SAM Decoding: Speculative Decoding via Suffix Automaton](https://mlsanity.com/paper/2411.10666/) (2024)
- [Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks](https://mlsanity.com/paper/2403.04814/) (2024)
- [PLD+: Accelerating LLM inference by leveraging Language Model Artifacts](https://mlsanity.com/paper/2412.01447/) (2024)
- [Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference](https://mlsanity.com/paper/2405.18628/) (2024)

## Built on by (most cited first, 6 of 6)

- [Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?](https://mlsanity.com/paper/2506.12713/) (2025)
- [When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding](https://mlsanity.com/paper/2511.01282/) (2025)
- [LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability](https://mlsanity.com/paper/2510.24345/) (2025)
- [To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals](https://mlsanity.com/paper/2609.20186/) (2026)
- [Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets](https://mlsanity.com/paper/2602.10583/) (2026)
- [Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.10046/) (2026)

## Abstract (arXiv)

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies repeated sequences in the model's chat history or context and speculates that the same tokens will follow, enabling seamless copying without compromising output quality and without requiring additional GPU memory. To evaluate the effectiveness of our approach, we conducted experiments using seven LLMs and five datasets: MT-Bench, CNN/DM, GSM8K, HumanEval, and our newly created dataset, MT-Redundant. MT-Redundant, introduced in this paper, transforms the second turn of MT-Bench into a request for variations of the first turn's answer, simulating real-world scenarios where users request modifications to prior responses. Our results demonstrate significant speed-ups: up to 2.35x on CNN/DM, 3.08x on the second turn of select MT-Redundant categories, and 2.66x on the third turn of GSM8K's self-correction tasks. Importantly, we show that CopySpec integrates seamlessly with speculative decoding, yielding an average 49% additional speed-up over speculative decoding for the second turn of MT-Redundant across all eight categories. While LLMs, even with speculative decoding, suffer from slower inference as context size grows, CopySpec leverages larger contexts to accelerate inference, making it a faster complementary solution. Our code and dataset are publicly available at https://github.com/RazvanDu/CopySpec.