Dual-View Training for Instruction-Following Information Retrieval
Summary
A dual-view data synthesis method using polarity reversal boosts instruction-following retrieval performance by 45% on the FollowIR benchmark.
View Cached Full Text
Cached at: 04/22/26, 06:17 AM
Paper page - Dual-View Training for Instruction-Following Information Retrieval
Source: https://huggingface.co/papers/2604.18845
Abstract
A dual-view data synthesis approach using polarity reversal enhances retrieval systems’ ability to follow instructions by training models to distinguish between topic-relevant and instruction-compliant documents.
Instruction-following information retrieval(IF-IR) studiesretrieval systemsthat must not only find documents relevant to a query, but also obeyexplicit user constraintssuch asrequired attributes,exclusions, oroutput preferences. However, most retrievers are trained primarily for semantic relevance and often fail to distinguish documents that match the topic from those that satisfy the instruction. We propose a dual-viewdata synthesisstrategy based onpolarity reversal: given a query, a document that is relevant under the instruction, and a hard negative that matches the query but violates the instruction, we prompt anLLMto generate acomplementary instructionunder which the two documents swaprelevance labels. By presenting the same document pair undercomplementary instructions that invert theirrelevance labels, thetraining signalforces the retriever to reconsider the same candidate set through the instruction, rather than relying on fixed topical cues. On a 305M-parameterencoder, our method improves performance on theFollowIR benchmarkby 45%, surpassinggeneral-purpose embedding modelsof comparable or larger scale. Through head-to-head comparisons at matched data budgets, we further show thatdata diversityandinstruction supervisionplay complementary roles: the former preserves general retrieval quality, while the latter improves instruction sensitivity. These results highlight the value of targeteddata synthesisfor buildingretrieval systemsthat are both broadly capable and instruction-aware.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2604\.18845
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2604.18845 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2604.18845 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2604.18845 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
Boosting Visual Instruction Tuning with Self-Supervised Guidance
This paper proposes augmenting visual instruction tuning in multimodal language models with self-supervised tasks expressed as natural language instructions, improving vision-centric reasoning without additional architecture or annotations. By reformulating classical self-supervised pretext tasks as image-instruction-response triplets, the method achieves consistent performance improvements across multiple benchmarks by injecting only 3-10% visually grounded instructions into the training data.
VCIFBench: Evaluating Complex Instruction Following for Video Understanding
VCIFBench is a new benchmark for evaluating complex instruction following in video understanding, featuring 306 test instructions with content, format, style, and structure constraints, plus a DPO preference dataset. Experiments on 10 MLLMs reveal that joint constraint satisfaction remains challenging, and DPO training on the benchmark data improves instruction-following performance.
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
This paper introduces Regret Pre-training, a self-supervised framework that uses a dual-view architecture to incorporate future context into causal language model training, improving performance on downstream tasks by up to 18 percentage points without adding parameters.
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
HyperEyes is a parallel multimodal search agent that uses dual-grained reinforcement learning to optimize inference efficiency, achieving higher accuracy with significantly fewer tool-call rounds compared to existing agents.
Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing Modalities
RL4IL introduces a reinforcement learning-guided retrieval method that uses soft fusion over frozen demonstration libraries to handle missing sensor modalities in robotic imitation learning at inference time, achieving high success rates under complete camera dropout.