LLM Prompting

LLM prompting explores how to effectively guide large language models (LLMs) to perform specific tasks by carefully crafting input instructions, or "prompts." Current research focuses on improving prompt design for diverse applications, including machine translation, information retrieval, and image generation, often employing techniques like ensemble prompting, retrieval-augmented prompting, and schema-guided prompting to enhance performance. These advancements are significant because they allow leveraging the power of LLMs without extensive fine-tuning, leading to more efficient and adaptable AI systems across various domains. Furthermore, research is actively addressing limitations in LLM understanding of nuanced logical relationships, such as directional inference, highlighting the need for more robust evaluation benchmarks.

Papers

April 7, 2024

Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language
Raphaël Merx, Aso Mahmudi, Katrina Langford, Leo Alberto de Araujo, Ekaterina Vylomova
Large Language Model Machine Translation Study Feature Low Resource Language Translation Performance Novel Corpus LLM Prompting

April 4, 2024

GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation
Kaustubh Dhole, Eugene Agichtein
Pseudo Relevance Feedback Prompt Ensemble LLM Prompting Query Reformulation

December 13, 2023

Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision
Shengguang Wu, Zhenglun Chen, Qi Su
Text to Image Synthesis Single Learning Higher Resolution Image LLM Prompting

October 23, 2023

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models
Gabriel Sarch, Yue Wu, Michael J. Tarr, Katerina Fragkiadaki
Language Model Open Domain Open Ended Human Robot Frozen Large Language Model LLM Prompting Prompt Example

October 10, 2023

Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction
Cheng Peng, Xi Yang, Kaleb E Smith, Zehao Yu, Aokun Chen, Jiang Bian, Yonghui Wu
Large Language Model Prompt Tuning Soft Prompt Biomedical Concept Frozen Large Language Model LLM Prompting Model Tuning

June 15, 2023

MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification
Hongyuan Dong, Weinan Zhang, Wanxiang Che
Metric Library Text Classification Task Shot Text Classification Relevance Modeling Relevance Ranking LLM Prompting

May 15, 2023

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng
Large Language Model LLM Prompting

October 10, 2022

Language Models Are Poor Learners of Directional Inference
Tianyi Li, Mohammad Javad Hosseini, Sabine Weber, Mark Steedman
Language Model Textual Entailment Weak Learner Entailment Graph LLM Prompting Directional Inference

LLM Prompting

Papers

Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language

GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation

Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction

MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

Language Models Are Poor Learners of Directional Inference