Context-Enhanced Contrastive Search for Improved LLM Text Generation
Not on the map. Why?
Abstract (arXiv)
Recently, Large Language Models (LLMs) have demonstrated remarkable advancements in Natural Language Processing (NLP). However, generating high-quality text that balances coherence, diversity, and relevance remains challenging. Traditional decoding methods, such as bean search and top-k sampling, often struggle with either repetitive or incoherent outputs, particularly in tasks that require long-form text generation. To address these limitations, the paper proposes a novel enhancement of the well-known Contrastive Search algorithm, Context-Enhanced Contrastive Search (CECS) with contextual calibration. The proposed scheme introduces several novelties including dynamic contextual importance weighting, multi-level Contrastive Search, and adaptive temperature control, to optimize the balance between fluency, creativity, and precision. The performance of CECS is evaluated using several standard metrics such as BLEU, ROUGE, and semantic similarity. Experimental results demonstrate significant improvements in both coherence and relevance of the generated texts by CECS outperforming the existing Contrastive Search techniques. The proposed algorithm has several potential applications in the real world including legal document drafting, customer service chatbots, and content marketing.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 22 Apr 2025.
Builds on
22 of 29 references.
References · 22
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
- 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
- 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
- 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
- 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
- 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 843
- 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
- 2019Neural Text Generation with Unlikelihood Trainingcited by 503
10 more
- 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
- 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
- 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
- 2024A Thorough Examination of Decoding Methods in the Era of LLMscited by 114
- 2022Locally Typical Samplingcited by 111
- 2022Contrastive Search Is What You Need For Neural Text Generationcited by 59
- 2022Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMETcited by 41
- 2023Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Modelscited by 38
- 2024Decoding Speculative Decodingcited by 34
- 2024LongGenBench: Long-context Generation Benchmarkcited by 28
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.