AION
Research paperRetrieval, RAG & Search1 source · Oct 7, 2026

Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models

Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt.

Fine-tuning
Read at arXiv (AI, ML, NLP, CV, robotics, multi-agent) ↗← Front page

Key points

  • Several new datasets and studies have examined this setting, showing that the current embedding models often struggle to follow such instructions reliably.
  • In this paper, we study the mechanism of how instructions actually affect the representations of retrieval queries in asymmetric retrieval tasks.
  • We show that models can fail to follow even simple task instructions when query-side distractors are included in the evaluation.
  • We hypothesize that this behavior is driven by the training setup of current embedding models and their evaluation, and show that fine-tuning with added query-side distractors leads to substantial improvements, with minimal effect on other tasks.

Sources (1)

  • [1]Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
    arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:51 PM
    Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt.
    Several new datasets and studies have examined this setting, showing that the current embedding models often struggle to follow such instructions reliably.

Extractive summary: sentences quoted from the sources.

Before this

  1. Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
  2. Oct 7, 2026Q-Learning with Scalar Adjoint Matching
  3. Oct 6, 2026Unlocking Earth AI’s planetary geospatial foundation models for global public health
  4. Oct 6, 2026Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
  5. Oct 1, 2026Introducing Clef: our open-source decision models, and new RL fine-tuning platform
  6. Sep 30, 2026Expanding AI Storage Access with NVIDIA cuObject and the NVIDIA SCADA Server SDK

Related

Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)5d ago

Learning to Retrieve via Reinforcement Learning in Embedding Space

Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)3d ago

Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval

Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)4d ago

Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA

Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)5d ago

UNREAL: Unifying Retrieval and Long-Context with a Single Model