mlsanityData to 14 Oct 2026

Learning from Contrastive Prompts: Automated Optimization and Adaptation

arXiv 2409.15199 ↗First posted 23 Sep 2024cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance. Additionally, an unexplored challenge in the literature is prompts effective for prior models may not perform well on newer versions or different languages. We propose the Learning from Contrastive Prompts (LCP) framework to address these gaps, enhancing both prompt optimization and adaptation. LCP employs contrastive learning to generate effective prompts by analyzing patterns in good and bad prompt examples. Our evaluation on the Big-Bench Hard dataset shows that LCP has a win rate of over 76% over existing methods in prompt optimization and demonstrates strong adaptability across different model versions, families, and languages. LCP offers a systematic approach to prompt engineering, reducing manual effort in deploying LLMs across varied contexts.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 23 Sep 2024.

Builds on

24 of 33 references.

References · 24

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  10. 2023Large Language Models as Optimizerscited by 864
  11. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  12. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
12 more
  1. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 333
  2. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  3. 2024TextGrad: Automatic "Differentiation" via Textcited by 273
  4. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  5. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 193
  6. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 100
  7. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  8. 2023Better Zero-Shot Reasoning with Self-Adaptive Promptingcited by 52
  9. 2023AutoHint: Automatic Prompt Optimization with Hint Generationcited by 30
  10. 2022Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Promptcited by 25
  11. 2023Robust Prompt Optimization for Large Language Models Against Distribution Shiftscited by 19
  12. 2023On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025What Prompts Don't Say: Understanding and Managing Underspecification in LLM Promptscited by 32
  2. 2025RLTHF: Targeted Human Feedback for LLM Alignmentcited by 8
  3. 2025A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithmcited by 6
  4. 2025Prototype-Based Dynamic Steering for Large Language Modelscited by 6
  5. 2026AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systemscited by 3
  6. 2025Learning Virtual Machine Scheduling in Cloud Computing through Language Agentscited by 1
  7. 2026ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysiscited by 1