Winning Amazon KDD Cup'24

TL;DR

This paper presents the winning solution for Amazon KDD Cup 2024, employing fine-tuned LLMs with data augmentation, distribution shift adaptation, and efficient inference techniques to excel across diverse online shopping tasks.

Contribution

The paper introduces a unified approach using fine-tuned Qwen2-72B-Instruct models, data augmentation, and advanced inference methods to achieve top results in a multi-task online shopping challenge.

Findings

Achieved first place in all tracks of KDD Cup 2024.

Developed a large training dataset from public sources and LLM augmentation.

Implemented efficient inference with quantization and vLLM to meet time constraints.

Abstract

This paper describes the winning solution of all 5 tasks for the Amazon KDD Cup 2024 Multi Task Online Shopping Challenge for LLMs. The challenge was to build a useful assistant, answering questions in the domain of online shopping. The competition contained 57 diverse tasks, covering 5 different task types (e.g. multiple choice) and across 4 different tracks (e.g. multi-lingual). Our solution is a single model per track. We fine-tune Qwen2-72B-Instruct on our own training dataset. As the competition released only 96 example questions, we developed our own training dataset by processing multiple public datasets or using Large Language Models for data augmentation and synthetic data generation. We apply wise-ft to account for distribution shifts and ensemble multiple LoRA adapters in one model. We employed Logits Processors to constrain the model output on relevant tokens for the tasks. AWQ 4-bit Quantization and vLLM are used during inference to predict the test dataset in the time constraints of 20 to 140 minutes depending on the track. Our solution achieved the first place in each individual track and is the first place overall of Amazons KDD Cup 2024.