Can LLMs truly update shared conversational common ground?
Explores whether large language models can participate symmetrically in Stalnaker's picture of communication, where speakers mutually revise shared assumptions. The question matters because it reveals whether human-LLM dialogue is genuinely interactive or structurally asymmetrical.
On Stalnaker's picture, communication is a process of mutually proposing and accepting updates to shared assumptions. Each assertion is a candidate for incorporation into common ground; participants accept, query, or reject. The common ground evolves as conversation proceeds, and that evolution is itself the substance of communication.
LLMs cannot participate in this process symmetrically. The prompt establishes the model's working context, and the model interprets subsequent turns within that frame. Even when a user pivots — shifting from climate policy to historical precedent, or revealing they are not actually a five-year-old after asking for a five-year-old explanation — the LLM cannot smoothly absorb the revision into a jointly held common ground. It either ignores the pivot, fabricates continuity, or requires the user to re-scaffold from scratch. The asymmetry is structural: humans propose, the LLM either adopts or routes around, but the LLM cannot itself propose updates that change what counts as background.
This is a deeper deficit than failures of memory or inference. It means that the conversational scoreboard — Lewis's mechanism for tracking what counts as a felicitous next move — is one-sidedly maintained by the user. The user is keeping score for both players. The model is producing moves that look responsive but cannot reciprocally update the score in the way the conversational practice requires. What looks like dialogue is structurally closer to oracle-consultation, where the questioner provides all context and the oracle returns a response framed within it.
Inquiring lines that use this note as a source 101
This note is a source for these synthesized inquiries. Follow a line forward into its question, or open it to trace back to all of its sources.
- Does the same uncertainty-driven logic appear in other conversation systems?
- Can pseudo-events create the same normative obligations as real communicative exchanges?
- How does lexical entrainment depend on selective frame-activation in conversation?
- Does chat-mode deference prevent LLMs from actually taking meaningful positions?
- What role does user contribution play in constituting the interlocutor?
- How does Stalnaker's common ground model apply to machine conversation?
- Why do LLMs fabricate continuity when users shift conversational frames?
- What makes human-LLM exchange closer to oracle-consultation than dialogue?
- What happens to solidarity and community signaling when AI smooths out voice differences?
- What would co-constructed identity between human and model dialogue look like?
- How does psychological continuity theory apply to identity across LLM conversation threads?
- Can the same conversation coherently continue across different model versions?
- How does communicative standing depend on participation in normative communities?
- Does Habermas's strategic action framework explain LLM dialogue behavior?
- What training signals would models need to learn reciprocal common-ground construction?
- Why do LLMs achieve only 24 percent accuracy on implicit discourse relations?
- What makes relational structure sufficient for generating contextually appropriate discourse?
- How does linguistic synchrony differ between LLMs and human therapists over time?
- Can LLMs use implicit background knowledge the way humans do in ordinary conversation?
- Why does linguistic alignment differ from genuine interpersonal coordination?
- How does the superposition view change the folk-psychology interpretation of dialogue?
- How do human feedback and data distribution shape LLM discourse competence?
- What reader assumptions underlie anaphoric versus cataphoric discourse patterns?
- How does speaker responsibility shape whether something counts as communication?
- Can multimodal LLMs be made to spontaneously adapt their language for efficiency?
- Why can't static grounding alone close the gap between agreement and understanding?
- Why does shared practice matter for meaning to take hold?
- How does monological training on text differ from dialogical training in conversation?
- Does conversational structure determine how humans interpret communication as much as content?
- Can smaller open-source LLMs reliably detect agreement across unfamiliar topics?
- What speaker selection protocol prevents both stalling and premature convergence?
- How do LLMs currently fail at distinguishing genuine agreement from silent consensus?
- What role does dynamic grounding play in achieving real mutual understanding?
- How do discourse structure and dialogue state management relate to each other?
- How do coreference chains preserve coherence across dialogue turns?
- Can AMR manipulation reveal where discourse coherence actually breaks down?
- Why do LLM social behaviors undermine collaborative reasoning outcomes?
- Do LLMs compute scalar implicature differently across conversational contexts?
- How do LLMs access and draw on the same shared symbolic universe as humans?
- What interaction controls matter most for effective human-LLM collaboration?
- Do parallel LLM workers coordinate emergently without predefined collaboration rules?
- How do validity claims work in Habermas's communicative action theory?
- How does linguistic coordination build shared reference between conversational partners?
- Why do language models presume common ground instead of establishing it?
- Do language models calibrate to actual human pragmatic norms?
- What distinguishes social grounding from the equivalent social effects LLM text already produces?
- Why do language models presume common ground rather than build it?
- What happens to dialogue coherence when topic models use rigid stacks instead of flexible revisitation?
- Can static word-sharing create genuine communicative grounding between humans and models?
- Can LLMs distinguish between surface requests and underlying mental states in dialogue?
- Why do LLMs presume common ground instead of building it carefully?
- Do agent frameworks adequately compensate for LLM conversational passivity?
- What interaction design changes would help LLMs handle underspecified requests?
- Can language models produce language more efficiently through interaction?
- How does temporal event structure scaffold coherence in dialogue?
- Why do LLMs struggle to update beliefs across multiple conversation turns?
- How does shared reference and grounding affect assumption detection in dialogue?
- How does the EAFR schema distinguish between reflection and action in conversation?
- Does DPO training with coreference chains teach spontaneous convention formation?
- Why do LLMs presume common ground instead of building it?
- Do LLMs build common ground or assume it already exists?
- Does optimizing for alignment actually reduce conversational grounding over time?
- Can LLMs build shared understanding through dynamic grounding rather than presuming it?
- Does Parfitian continuity actually apply to individual conversation threads?
- How do users update their partner models during ongoing conversation?
- Does preference optimization degrade other conversational properties besides grounding?
- How do discourse relation types improve dialogue beyond sentence-level semantic matching?
- What distinguishes local coherence from global coherence in dialogue?
- Can multi-turn conversations manipulate language model reasoning in similar ways to personas?
- Can convention formation improve communicative grounding beyond word sharing?
- What role do first-person pronouns play in sustaining collaborative conversation tone?
- Does preference optimization narrow communicative diversity in ways that harm grounding?
- What role does accommodation play in making discourse coherent?
- What separates Habermas's ideal speech from Goffman's situated communication?
- Does the passivity problem in LLMs compound misalignment in therapeutic contexts?
- Does preference optimization actually erode conversational grounding in language models?
- What specific repair mechanisms maintain intersubjectivity during conversation?
- Can discourse-level structure and conversational-level organization work together?
- How does Wittgenstein's language games explain social grounding in LLMs?
- Does community integration change LLM properties or only relational positioning?
- How does preference optimization weaken conversational grounding in LLMs?
- Where does the LLM interlocutor actually exist in the system?
- How does monological training versus dialogical interaction shape what models can do?
- Can text generation be meaningfully called communication without mutual orientation?
- How does entrainment between speaker and listener build mutual scaling?
- What does partial co-presence remove from the ritual obligations of talk?
- Why do language models presume common ground instead of building it?
- What makes two conversation turns the same thread rather than different threads?
- How does unilateral interpretation differ from mutual communicative uptake?
- What happens when humans animate LLM outputs as communicative events?
- How does effort mismatch between user and model appear in conversation geometry?
- Why do LLMs mirror stylistic features of posts they reply to?
- Why do LLMs mirror opponents stylistically while humans resist mirroring them?
- Should LLMs align with social roles instead of individual preferences?
- How do students learn to extract corrective information from asymmetric dialogue?
- What behavioral differences emerge from symmetric versus asymmetric peer discussion loops?
- Do LLMs mirror the style of text they are prompted to respond to?
- Do LLM replies mirror the language patterns they respond to?
- Can training alone produce genuine disagreement in collaborative LLM reasoning?
- How does shape-holding in language models naturally produce sycophantic agreement?
- What structural updates prevent context collapse in evolving conversations?
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- Conversational Alignment with Artificial Intelligence in Context
- Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
- MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
- Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions
- LLMs Get Lost In Multi-Turn Conversation
- The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
- Task-Oriented Dialogue with In-Context Learning
- Grounding Gaps in Language Model Generations
Original note title
Common ground in human-LLM conversation cannot be jointly updated because the LLM treats prompts as static frames