kiyam/ddro-nq-dataset

Tasks

• text-retrieval

Citation text from the card

@article{mekonnen2025lightweight,
author = {Mekonnen, Kidist Amde and Tang, Yubao and de Rijke, Maarten},
title = {Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval},
year = {2025},
isbn = {9798400715921},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3726302.3730023},
doi = {10.1145/3726302.3730023},
abstract = {Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task, allowing for end-to-end optimization toward a unified global retrieval objective. However, existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. While reinforcement learning-based methods, such as reinforcement learning from relevance feedback (RLRF), aim to address this misalignment through reward modeling, they introduce significant complexity, requiring the optimization of an auxiliary reward function followed by reinforcement fine-tuning, which is computationally expensive and often unstable. To address these challenges, we propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking, eliminating the need for explicit reward modeling and reinforcement learni

All datasets marked Permissive or share-alike | JSON