Metraipolis › archive › dc_0ef12443e685

When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency — arXiv:2611.02273

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02273
License (as archived)
CC0-1.0
Archived
2026-11-03T18:24:40.462Z
SHA-256 of the archived text
8bc7aa6c4e97c033adc13de8b01861604c19b46913ce19a7bd850a3bf729a028
Stable URL of this page
https://metraipolis.com/documento/dc_0ef12443e685

How to cite

When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency — arXiv:2611.02273 — arXiv (en), https://arxiv.org/abs/2611.02273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ef12443e685 (Metraipolis archive dc_0ef12443e685, sha256 8bc7aa6c4e97c033adc13de8b01861604c19b46913ce19a7bd850a3bf729a028)
BibTeX
@misc{dc0ef12443e685,
  title = {When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency — arXiv:2611.02273},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02273},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ef12443e685; sha256 8bc7aa6c4e97c033adc13de8b01861604c19b46913ce19a7bd850a3bf729a028},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used to annotate text for social science research, content moderation, and training data. Their broad knowledge of real-world entities raises a concern: when labeling a text, do they rely on its evidence or substitute what they already know? We call this behavior a memory shortcut and examine when it emerges, what amplifies it, and how to mitigate it. Using 995 widely recognized public figures and four matched control names per figure, we construct counterfactual texts that separate textual evidence from prior knowledge, and evaluate three commercial LLMs on 121,594 prompts each across five stages. We find a striking asymmetry. Although all models recognize nearly every figure, none follows memory over the text when the two conflict. Shortcuts instead emerge when evidence is absent: for one model, famous names raise the rate of remembered occupations, ages, and countries by 17.0, 14.9, and 6.8 percentage points relative to synthetic names. These effects occur only for recognized figures, and 98.6% of the resulting labels are factually correct about the namesake while none is supported by the text. Evaluation threats and answer-contingent rewards amplify shortcuts by 8.7 and 12.4 points. Famous names also raise leadership ratings of sparsely documented applicants by 0.22 and 0.28 points in two models. A namesake reminder and name masking each eliminate the shortcuts, with trade-offs in gender annotation. LLM annotations can thus be factually correct yet methodologically invalid. Trustworthy LLM annotation requires audits that test evidence absence, account for incentives in annotation instructions, and evaluate the attribute-specific trade-offs of mitigation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.02273 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:10:08.046Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).