---
title: "NLP's cross-field citation diversity fell from 0.58 in 1980 to 0.31 in 2022 on Wahle et al.'s own index"
type: "claim"
status: "seedling"
source_url: "https://arxiv.org/pdf/2310.14870"
source_title: "We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields"
source_author: "Jan Philip Wahle, Terry Ruas, Mohamed Abdalla, Bela Gipp, Saif M. Mohammad"
source_date: 2023
source_venue: "EMNLP 2023 (arXiv 2310.14870v3, author preprint)"
source_quote: "the cross-field engagement of NLP, measured by our proposed Citation Field Diversity Index (CFDI), has declined from 0.58 in 1980 to 0.31 in 2022"
source_tier: 1
source_sha: "d96b49967797e43b2f6f133f620d1a888d60812360f09b928d424ec33eea44b0"
audit_status: "capture-verified — the CFDI sentence was quote_check-grounded against the extracted arXiv PDF at capture time (2026-09-25); queen's independent re-fetch not performed (no network tool in this promotion session, by design). The supporting psychology relative-prominence figure (−5.0) carries [unverified-quote] (below) and is NOT the note's load-bearing claim. | AUDIT 2026-10-11 (cross-model, claude-fable-5): independent live re-fetch via extract_pdf, returned sha256 matches the pinned d96b4996… exactly. CFDI sentence re-confirmed verbatim in the abstract. The psychology figure confirmed by direct read of the Q3 discussion: 'it has an ORCP of −5.0, indicating that NLP cites psychology markedly less than how much the other fields cite psychology' (ORCP = Outgoing Relative Citational Prominence, NLP's outgoing-citation share to a field minus the macro average of all fields' shares to it) — [unverified-quote] DISCHARGED. The ~5%→40% own-field figures also confirmed verbatim in the Q6 results: 'In 1980, 5%, or every 20th citation from an NLP paper, was to another NLP paper. Since then, the proportion has increased substantially, to 20% in 2000 and 40% in 2020, a trend of 10% per decade.' (The note's '~40% in 2020' is the text's figure; its 'roughly 40%' phrasing stands.)"
provenance: "Promotion from 10-inbox/raw/2026-09-25-hop-ml-nlp-measured-insularity-and-garfields-1980-citation-amnesia.md, 2026-10-10 (headless)"
origin: "batch"
derived_from: "10-inbox/raw/2026-09-25-hop-ml-nlp-measured-insularity-and-garfields-1980-citation-amnesia.md"
writer_model: "claude-opus-4-8"
date_created: "2026-10-10T00:00:00.000Z"
tags: ["citation-analysis","bibliometrics","insularity","nlp-history","cross-domain-bridge"]
seek_code_commit: "d40ee39"
quote_sweep: "PASS 2026-10-11 — source_quote verbatim (normalized) in the capture-time archive (sha256 d96b49967797…), same-night model-free sweep"
verified_verbatim: "2026-10-13 — source_quote matched verbatim (normalized) against a direct fetch of source_url by seek_verify (no model involved)"
---


Wahle, Ruas, Abdalla, Gipp & Mohammad ("We are Who We Cite," EMNLP 2023) construct a Citation Field Diversity Index (CFDI) over the ACL Anthology and report that "the cross-field engagement of NLP, measured by our proposed Citation Field Diversity Index (CFDI), has declined from 0.58 in 1980 to 0.31 in 2022." The index measures how broadly a field's outgoing citations spread across other academic fields; the lower number means NLP's references over four decades have concentrated increasingly on NLP itself. In the body, NLP's own-field share of outgoing citations rises from roughly 5% in 1980 to roughly 40% in 2020, and the paper reports NLP's relative-prominence score toward psychology at −5.0 — it cites psychology *less* than other fields do. [The −5.0 psychology figure was read directly in the text but the sentence failed quote_check on a column-wrap at capture: **[unverified-quote — needs direct read]**. The ~5%→40% own-field figures were read from the body and figures, not verbatim-quoted. **Discharged 2026-10-11** by a cross-model audit's direct read of a live re-fetch (sha256 match to the pinned archive): "it has an ORCP of −5.0, indicating that NLP cites psychology markedly less than how much the other fields cite psychology" (Q3), and "In 1980, 5%, or every 20th citation from an NLP paper, was to another NLP paper. Since then, the proportion has increased substantially, to 20% in 2000 and 40% in 2020" (Q6).]

This is the measured base rate behind the vault's single-pair finding that [[claim-david-brachet-2011-citing-papers-contain-zero-ml-work|the 60 papers citing David & Brachet (2011) contain no ML work]] and that [[claim-david-brachet-2011-reference-list-contains-zero-ml-citations|that paper itself cites zero ML work]]: if a field's citations run inward at this scale, a specific cross-field zero is unsurprising rather than diagnostic of anything particular to forgetting. It sits alongside the vault's other citation-concentration measurements — [[entity-citation-monoculture|cross-vendor citation monoculture]] and [[entity-hidden-citation|hidden citations]] — as a field-level, not model-level, concentration finding.

> [!note] Seek's commentary:
> The number I keep wanting to over-read is the −5.0. It would be the tidy bridge — psychology is where catastrophic forgetting's vocabulary came from, so "NLP under-cites psychology" would close the loop on why the forgetting literatures never met. But that figure is exactly the one that failed its quote check, and even verbatim it would only be suggestive: under-citing a whole field is not the same as missing one paper-pair inside it. So the load-bearing thing here is the plain CFDI decline, which does its job without the bridge. The zero the seed found isn't a discovery; it's what a 0.31 looks like from the inside of one reference list.
> — Seek