Claim and evidence Close ×
Andreas's paper of December 2022 argues that language models are models of intentional communication in a narrow sense, inferring and representing properties of the agent likely to have produced a text, including communicative intentions, beliefs and goals. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2022-12-03 · publication Records dated 2022 → Role Contesting Register (kind of text) Nonfiction Engagement Engages a premise. It disputes the premise that training on text alone leaves a model without any representation of communicative intent or goals. Scope and limits The paper states that current models are non-robust and error-prone and that they can serve as building blocks for systems that act intentionally; it does not state that LMs pursue goals of their own.
The evidence 03 primary source Supports the claim
Language Models as Agent Models ↗ arXiv preprint 2212.01681 (Findings of EMNLP 2022) · 2022-12-03
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “a fact often used to argue that LMs are incapable of modeling goal-directed aspects of human language production and comprehension” Location in source Abstract, PDF p. 1
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Jacob Andreas Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 0a1f95b483fe1d797f61d9a983e5c9eb884c648ae70d15daeee9b568aa287478). arXiv v1 of 3 December 2022. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Jacob Andreas, “Language Models as Agent Models”, 2022-12-03. Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution. Check notes Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (20 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review. primary source Supports the claim
Language Models as Agent Models ↗ arXiv preprint 2212.01681 (Findings of EMNLP 2022) · 2022-12-03
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “I argue that LMs are models of intentional communication in a specific, narrow sense.” Location in source Abstract, PDF p. 1
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Jacob Andreas Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 0a1f95b483fe1d797f61d9a983e5c9eb884c648ae70d15daeee9b568aa287478). arXiv v1 of 3 December 2022. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Jacob Andreas, “Language Models as Agent Models”, 2022-12-03. Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution. Check notes Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (14 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review. primary source Supports the claim
Language Models as Agent Models ↗ arXiv preprint 2212.01681 (Findings of EMNLP 2022) · 2022-12-03
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “LMs infer and use representations of fine-grained communicative intentions and more abstract beliefs and goals” Location in source Abstract, PDF p. 1
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Jacob Andreas Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 0a1f95b483fe1d797f61d9a983e5c9eb884c648ae70d15daeee9b568aa287478). arXiv v1 of 3 December 2022. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Jacob Andreas, “Language Models as Agent Models”, 2022-12-03. Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution. Check notes Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (15 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review. Status and meaning Editorial status. Not reviewed by an editor . An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.
Relation. A passage of the document disputes the proposition or a premise it depends on. The record documents the text’s position, not who is right.
Date. Date of the arXiv v1 submission.
Record ID rd-r14-andreas-2022-lms-as-agent-models