# The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA

Source: [The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA](<https://www.sota2.com/research/paper/68fa72551e209131cea55b50>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:23:12.204Z

Authors: Yiming Li, Zhao Zhang

Published: 2024-02-28T15:05:43.000Z

## Abstract

Conversational multi-doc question answering aims to answer specific questions based on the retrieved documents as well as the contextual conversations. In this paper, we introduce our winning approach for the "Conversational Multi-Doc QA" challenge in WSDM Cup 2024, which exploits the superior natural language understanding and generation capability of Large Language Models (LLMs). We first adapt LLMs to the task, then devise a hybrid training strategy to make the most of in-domain unlabeled data. Moreover, an advanced text embedding model is adopted to filter out potentially irrelevant documents and several approaches are designed and compared for the model ensemble. Equipped with all these techniques, our solution finally ranked 1st place in WSDM Cup 2024, surpassing its rivals to a large extent. The source codes have been released at https://github.com/zhangzhao219/WSDM-Cup-2024.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.18385>)

[PDF](<https://arxiv.org/pdf/2402.18385.pdf>)
