Research
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
arXiv:2610.10508v1 Announce Type: new Abstract: Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as
arXiv:2610.10508v1 Announce Type: new Abstract: 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. 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.
Related
- ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation
- DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
- Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval
- Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters
Source: arXiv cs.CL | 2026-10-08