# An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation

arXiv: https://arxiv.org/abs/2211.10797 · HTML: https://mlsanity.com/paper/2211.10797/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 19 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [Contrastive Search Is What You Need For Neural Text Generation](https://mlsanity.com/paper/2210.14140/) (2022)
- [Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory](https://mlsanity.com/paper/2004.02214/) (2020)

## Built on by (most cited first, 14 of 14)

- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective](https://mlsanity.com/paper/2310.10226/) (2023)
- [MAUVE Scores for Generative Models: Theory and Practice](https://mlsanity.com/paper/2212.14578/) (2022)
- [A Frustratingly Simple Decoding Method for Neural Text Generation](https://mlsanity.com/paper/2305.12675/) (2023)
- [Look-back Decoding for Open-Ended Text Generation](https://mlsanity.com/paper/2305.13477/) (2023)
- [Statistical Multicriteria Evaluation of LLM-Generated Text](https://mlsanity.com/paper/2506.18082/) (2025)
- [Language Model Decoding as Direct Metrics Optimization](https://mlsanity.com/paper/2310.01041/) (2023)
- [Speculative Contrastive Decoding](https://mlsanity.com/paper/2311.08981/) (2023)
- [A Statistical Case Against Empirical Human-AI Alignment](https://mlsanity.com/paper/2502.14581/) (2025)
- [Momentum Decoding: Open-ended Text Generation As Graph Exploration](https://mlsanity.com/paper/2212.02175/) (2022)
- [MACD: Model-Aware Contrastive Decoding via Counterfactual Data](https://mlsanity.com/paper/2602.01740/) (2026)
- [Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption](https://mlsanity.com/paper/2502.11723/) (2025)
- [On the performativity of SDG classifications in large bibliometric databases](https://mlsanity.com/paper/2405.03007/) (2024)

## Abstract (arXiv)

In the study, we empirically compare the two recently proposed decoding methods, i.e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation. The automatic evaluation results suggest that, while CS performs worse than CD on the MAUVE metric, it substantially surpasses CD on the diversity and coherence metrics. More notably, extensive human evaluations across three different domains demonstrate that human annotators are universally more in favor of CS over CD with substantial margins. The contradicted results between MAUVE and human evaluations reveal that MAUVE does not accurately reflect human preferences. Therefore, we call upon the research community to develop better evaluation metrics for open-ended text generation. To ensure the reproducibility of our work, we have open-sourced all our code, evaluation results, as well as human annotations at https://github.com/yxuansu/Contrastive_Search_versus_Contrastive_Decoding.