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

Yiming Li, Zhao Zhang
2/28/2024
cs.CLcs.AI

Official code: zhangzhao219/WSDM-Cup-2024 (157 stars, last commit 2025-07-25).

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.

View on arXivView PDF

Code Implementations(1)

zhangzhao219/WSDM-Cup-2024Official100%

1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc

15719Shell, PythonFeb 16, 20241 years ago

Similar Papers

DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections

83% match2025

Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities

83% match1 repo1632025

Automatic Question-Answer Generation for Long-Tail Knowledge

82% match2024

FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models

82% match1 repo632024

Few-Shot Multilingual Open-Domain QA from 5 Examples

82% match1 repo2025

Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

82% match2024

Cite this paper

@article{li2024first,
  title  = {The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA},
  author = {Yiming Li and Zhao Zhang},
  year   = {2024},
  eprint = {2402.18385},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.18385v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.18385.svg)](https://codeofpaper.com/paper/2402.18385)

Discussion