# MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering

arXiv: https://arxiv.org/abs/2412.15540 · HTML: https://mlsanity.com/paper/2412.15540/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks](https://mlsanity.com/paper/2010.08240/) (2020)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [Complex Temporal Question Answering on Knowledge Graphs](https://mlsanity.com/paper/2109.08935/) (2021)
- [Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?](https://mlsanity.com/paper/2406.13121/) (2024)
- [Efficient Document Re-Ranking for Transformers by Precomputing Term Representations](https://mlsanity.com/paper/2004.14255/) (2020)
- [AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge](https://mlsanity.com/paper/2412.13670/) (2024)
- [AKEW: Assessing Knowledge Editing in the Wild](https://mlsanity.com/paper/2402.18909/) (2024)
- [A Memory Efficient Baseline for Open Domain Question Answering](https://mlsanity.com/paper/2012.15156/) (2020)
- [Who's Who: Large Language Models Meet Knowledge Conflicts in Practice](https://mlsanity.com/paper/2410.15737/) (2024)
- [SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA](https://mlsanity.com/paper/2409.16682/) (2024)
- [Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation](https://mlsanity.com/paper/2110.04889/) (2021)
- [Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback](https://mlsanity.com/paper/2410.21242/) (2024)

## Built on by (most cited first, 17 of 17)

- [Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models](https://mlsanity.com/paper/2502.01386/) (2025)
- [Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective](https://mlsanity.com/paper/2505.15045/) (2025)
- [It's High Time: A Survey of Temporal Question Answering](https://mlsanity.com/paper/2505.20243/) (2025)
- [RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge](https://mlsanity.com/paper/2510.13590/) (2025)
- [mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.24073/) (2025)
- [Reading Between the Timelines: RAG for Answering Diachronic Questions](https://mlsanity.com/paper/2507.22917/) (2025)
- [DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes](https://mlsanity.com/paper/2505.17162/) (2025)
- [Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space](https://mlsanity.com/paper/2602.06056/) (2026)
- [Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety](https://mlsanity.com/paper/2605.12729/) (2026)
- [ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval](https://mlsanity.com/paper/2605.03361/) (2026)
- [DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.01212/) (2026)
- [Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding](https://mlsanity.com/paper/2608.08512/) (2026)
- [A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.12282/) (2025)
- [Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval](https://mlsanity.com/paper/2509.01306/) (2025)
- [Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation](https://mlsanity.com/paper/2604.14169/) (2026)
- [FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.14227/) (2026)
- [Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall](https://mlsanity.com/paper/2609.33183/) (2026)

## Abstract (arXiv)

Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Existing approaches either update the parametric knowledge of LLMs with new facts, which is resource-intensive and often impractical, or integrate LLMs with external knowledge retrieval (i.e., retrieval-augmented generation). However, off-the-shelf retrievers often struggle to identify relevant documents that require intensive temporal reasoning. To systematically study time-sensitive question answering, we introduce the TempRAGEval benchmark, which repurposes existing datasets by incorporating temporal perturbations and gold evidence labels. As anticipated, all existing retrieval methods struggle with these temporal reasoning-intensive questions. We further propose Modular Retrieval (MRAG), a trainless framework that includes three modules: (1) Question Processing that decomposes question into a main content and a temporal constraint; (2) Retrieval and Summarization that retrieves evidence and uses LLMs to summarize according to the main content; (3) Semantic-Temporal Hybrid Ranking that scores each evidence summarization based on both semantic and temporal relevance. On TempRAGEval, MRAG significantly outperforms baseline retrievers in retrieval performance, leading to further improvements in final answer accuracy.