SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generation with LLMs

arXiv:2508.08742 · cs.CL, cs.AI · Submitted 2025-08-12 · Read on arXiv

cs.CL, cs.AI

Submitted: 2025-08-12

Updated: 2026-10-12

Code: https://github.com/netease-youdao/BCEmbedding

Terminology

• RAG — 4× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes

Sources

• Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation
• LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
• InternLM2 Technical Report
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Don't Forget to Connect! Improving RAG with Graph-based Reranking
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Mathematical Problem Solving With the MATH Dataset
• Mistral 7B
• FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research
• PubMedQA: A Dataset for Biomedical Research Question Answering
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
• Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
• DeepSeek-V3 Technical Report
• Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
• Are large language models superhuman chemists?
• OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts
• SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models
• PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering