# NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework

arXiv: https://arxiv.org/abs/2212.00229 · HTML: https://mlsanity.com/paper/2212.00229/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2022.

## Built on by (most cited first, 5 of 5)

- [BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval](https://mlsanity.com/paper/2305.11052/) (2023)
- [I3: Intent-Introspective Retrieval Conditioned on Instructions](https://mlsanity.com/paper/2308.10025/) (2023)
- [Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations](https://mlsanity.com/paper/2408.11415/) (2024)
- [XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare](https://mlsanity.com/paper/2405.06270/) (2024)
- [Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications](https://mlsanity.com/paper/2602.22219/) (2025)

## Abstract (arXiv)

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g, pre-trained language models (PLMs) are hard to generalize. Mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with baselines.