mlsanityData to 14 Oct 2026

Speculative Contrastive Decoding

arXiv 2311.08981 ↗First posted 15 Nov 2023cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative decoding and contrastive decoding, we introduce Speculative Contrastive Decoding~(SCD), a straightforward yet powerful decoding approach that leverages predictions from smaller language models~(LMs) to achieve both decoding acceleration and quality improvement. Extensive evaluations and analyses on four diverse language tasks demonstrate the effectiveness of SCD, showing that decoding efficiency and quality can compatibly benefit from one smaller LM.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

21 of 32 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2016Pointer Sentinel Mixture Modelscited by 3,096
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  10. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  11. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  12. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
9 more
  1. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  2. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  3. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 301
  4. 2022A Contrastive Framework for Neural Text Generationcited by 225
  5. 2023Speculative Decoding with Big Little Decodercited by 164
  6. 2023Accelerating LLM Inference with Staged Speculative Decodingcited by 151
  7. 2023Closing the Curious Case of Neural Text Degenerationcited by 32
  8. 2022An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generationcited by 14
  9. 2023Surfacing Biases in Large Language Models using Contrastive Input Decodingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 2.

8 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2024Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
  2. 2024Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding
  3. 2025Speculative Decoding: Performance or Illusion?
  4. 2024A Theoretical Perspective for Speculative Decoding Algorithm
  5. 2024SSSD: Simply-Scalable Speculative Decoding
  6. 2026Speculative Decoding and the Curse of Multilinguality
  7. 2026Speculative Decoding with a Speculative Vocabulary
  8. 2024Decoding Speculative Decoding