# Forgotten Knowledge: Examining the Citational Amnesia in NLP

arXiv: https://arxiv.org/abs/2305.18554 · HTML: https://mlsanity.com/paper/2305.18554/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 46 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 10 of 10)

- [The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research](https://mlsanity.com/paper/2305.02797/) (2023)
- [Examining Citations of Natural Language Processing Literature](https://mlsanity.com/paper/2005.00912/) (2020)
- [Geographic Citation Gaps in NLP Research](https://mlsanity.com/paper/2210.14424/) (2022)
- [Ethics Sheets for AI Tasks](https://mlsanity.com/paper/2107.01183/) (2021)
- [Gender Gap in Natural Language Processing Research: Disparities in Authorship and Citations](https://mlsanity.com/paper/2005.00962/) (2020)
- [D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research](https://mlsanity.com/paper/2204.13384/) (2022)
- [On the Shoulders of Giants: The Growing Impact of Older Articles](https://mlsanity.com/paper/1411.0275/) (2014)
- [Attention decay in science](https://mlsanity.com/paper/1503.01881/) (2015)
- [The Memory of Science: Inflation, Myopia, and the Knowledge Network](https://mlsanity.com/paper/1607.05606/) (2016)
- [Back to the past: on the shoulders of an academic search engine giant](https://mlsanity.com/paper/1603.09111/) (2016)

## Built on by (most cited first, 13 of 13)

- [It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk](https://mlsanity.com/paper/2310.01387/) (2023)
- [We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields](https://mlsanity.com/paper/2310.14870/) (2023)
- [From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP](https://mlsanity.com/paper/2406.12618/) (2024)
- [CiteAssist: A System for Automated Preprint Citation and BibTeX Generation](https://mlsanity.com/paper/2407.03192/) (2024)
- [Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields](https://mlsanity.com/paper/2402.12046/) (2024)
- [To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing](https://mlsanity.com/paper/2310.07715/) (2023)
- [On Tables with Numbers, with Numbers](https://mlsanity.com/paper/2408.06062/) (2024)
- [Transforming Scholarly Landscapes: Influence of Large Language Models on Academic Fields beyond Computer Science](https://mlsanity.com/paper/2409.19508/) (2024)
- [SciEvo: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis](https://mlsanity.com/paper/2410.09510/) (2024)
- [Is there really a Citation Age Bias in NLP?](https://mlsanity.com/paper/2401.03545/) (2024)
- [Beyond Linearity and Time-Homogeneity: Relational Hyper Event Models with Time-Varying Non-Linear Effects](https://mlsanity.com/paper/2509.05289/) (2025)
- [Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias](https://mlsanity.com/paper/2512.05714/) (2025)
- [How Should We Model the Probability of a Language?](https://mlsanity.com/paper/2602.08951/) (2026)

## Abstract (arXiv)

Citing papers is the primary method through which modern scientific writing discusses and builds on past work. Collectively, citing a diverse set of papers (in time and area of study) is an indicator of how widely the community is reading. Yet, there is little work looking at broad temporal patterns of citation. This work systematically and empirically examines: How far back in time do we tend to go to cite papers? How has that changed over time, and what factors correlate with this citational attention/amnesia? We chose NLP as our domain of interest and analyzed approximately 71.5K papers to show and quantify several key trends in citation. Notably, around 62% of cited papers are from the immediate five years prior to publication, whereas only about 17% are more than ten years old. Furthermore, we show that the median age and age diversity of cited papers were steadily increasing from 1990 to 2014, but since then, the trend has reversed, and current NLP papers have an all-time low temporal citation diversity. Finally, we show that unlike the 1990s, the highly cited papers in the last decade were also papers with the least citation diversity, likely contributing to the intense (and arguably harmful) recency focus. Code, data, and a demo are available on the project homepage.