Every Clause Counts: Instruction-Following Reranking by Multiplying Small, Answerable Questions
cs.IR, cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Task-aware Retrieval with Instructions
- The Llama 3 Herd of Models
- Mistral 7B
- Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
- Passage Re-ranking with BERT
- INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models
- GPT-4o System Card
- RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models
- RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
- Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
- One Embedder, Any Task: Instruction-Finetuned Text Embeddings
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
- Zephyr: Direct Distillation of LM Alignment
- Improving Text Embeddings with Large Language Models
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
- Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
- Rank1: Test-Time Compute for Reranking in Information Retrieval
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
- Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA