Co‐textual dopes: How LLMs produce contextually appropriate text in chat interactions with humans without access to context
Author:
Open Access
- 4 December 2025
- journal article
- Published by Wiley in Journal of Linguistic Anthropology
- Vol. 36 (1)
Abstract
This paper asks how LLM‐based systems can produce text that is taken as contextually appropriate by humans without having seen text in its broader context. To understand how this is possible, context and co‐text have to be distinguished. Co‐text is input to LLMs during training and at inference as well as the primary resource of sense‐making for humans in interaction, collaboratively produced by both human and machine during chat. Systems can also passively participate in contextualization, insofar as cues are found in the co‐text and the user guides the system as to what is the appropriate context for them.Keywords
Funding Information
- Ministerium für Kultur und Wissenschaft des Landes Nordrhein-Westfalen (NW21‐059A)
This publication has 48 references indexed in Scilit:
- AI in situated action: a scoping review of ethnomethodological and conversation analytic studiesAI & SOCIETY, 2024
- “Machine Down”: making sense of human–computer interaction—Garfinkel’s research on ELIZA and LYRIC from 1967 to 1969 and its contemporary relevanceAI & SOCIETY, 2023
- Language in Culture2022
- Common Understandings of and Consensus About Collective Action: The Transformation of Specifically Vague Proposals as a Collective AchievementHuman Studies, 2019
- Semantic Drift in ConversationsHuman Studies, 2012
- Talk in Action2010
- Sequence Organization in Interaction2007
- Die Analyse von Struktursicherungsoperationen als Kooperationsfeld von Konversationsanalyse, objektiver Hermeneutik und Systemtheorie1997
- Metapragmatic discourse and metapragmatic function1993
- The things we do with words: Ilongot speech acts and speech act theory in philosophyLanguage in Society, 1982