# Reading Between the Timelines: RAG for Answering Diachronic Questions

arXiv: https://arxiv.org/abs/2507.22917 · HTML: https://mlsanity.com/paper/2507.22917/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://mlsanity.com/paper/2312.07559/) (2023)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation](https://mlsanity.com/paper/2501.03225/) (2025)
- [Temporal Knowledge Question Answering via Abstract Reasoning Induction](https://mlsanity.com/paper/2311.09149/) (2023)
- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information](https://mlsanity.com/paper/2204.13032/) (2022)
- [MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering](https://mlsanity.com/paper/2412.15540/) (2024)
- [TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions](https://mlsanity.com/paper/2502.21024/) (2025)
- [ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages](https://mlsanity.com/paper/2403.17859/) (2024)
- [Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance](https://mlsanity.com/paper/2503.05185/) (2025)

## Built on by (most cited first, 4 of 4)

- [CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning](https://mlsanity.com/paper/2511.18659/) (2025)
- [Freshness and the Limits of Heuristic Trend Detection in Temporal RAG](https://mlsanity.com/paper/2509.19376/) (2025)
- [Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation](https://mlsanity.com/paper/2604.14169/) (2026)
- [IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval](https://mlsanity.com/paper/2606.06044/) (2026)

## Abstract (arXiv)

While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal queries that require tracking entities and phenomena across time. This blind spot arises because conventional, semantically-driven retrieval methods are not equipped to gather evidence that is both topically relevant and temporally coherent for a specified duration. We address this challenge by proposing a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic. Our methodology begins by disentangling a user's query into its core subject and its temporal window. It then employs a specialized retriever that calibrates semantic matching against temporal relevance, ensuring the collection of a contiguous evidence set that spans the entire queried period. To enable rigorous evaluation of this capability, we also introduce the Analytical Diachronic Question Answering Benchmark (ADQAB), a challenging evaluation suite grounded in a hybrid corpus of real and synthetic financial news. Empirical results on ADQAB show that our approach yields substantial gains in answer accuracy, surpassing standard RAG implementations by 13% to 27%. This work provides a validated pathway toward RAG systems capable of performing the nuanced, evolutionary analysis required for complex, real-world questions. The dataset and code for this study are publicly available at https://github.com/kwunhang/TA-RAG.