Line of inquiry
Inquiring lines›What makes reasoning better — more…›How do prompts and framing affect…›this line of inquiry
How do language models establish social grounding in human dialogue?
A broader line of inquiry — a family of 43 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 43
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Why do language models presume common ground rather than build it?
- Why do language models presume common ground instead of building it?
- Does social grounding in language improve through iterative human integration?
- Can language models develop genuine social grounding through human interaction?
- Can LLMs use implicit background knowledge the way humans do in ordinary conversation?
- How do LLMs differ from humans in their grounding mechanisms?
- Can convention formation improve communicative grounding beyond word sharing?
- How does Wittgenstein's language games explain social grounding in LLMs?
- Do LLMs build common ground or assume it already exists?
- Can static word-sharing create genuine communicative grounding between humans and models?
- How does implicit meaning processing limit LLM pragmatic reasoning?
- How do language models treat injected information as shared common ground?
- Why do LLMs presume common ground instead of building it?
- How does semantic grounding differ between human minds and language models?
- Can LLMs infer situational context the way humans do pragmatically?
- Why do LLMs lack the communicative scaffold that humans learn?
- Does functional grounding through discourse patterns count as genuine semantic meaning?
- Can LLMs build shared understanding through dynamic grounding rather than presuming it?
- Why do conventional mental models fail when applied to AI interaction?
- What makes social grounding different from constitutive linguistic agency?
- Can LLMs predict social norms without deep integration into linguistic practices?
- Does social grounding differ fundamentally from causal grounding in LLM behavior?
- Can LLMs participate meaningfully in discourse without consciousness or understanding?
- Can language models ground clarifications without vision and kinesthetic modalities?
- Can training LLMs to form ad-hoc conventions improve their pragmatic reasoning?
- Can functional semantic grounding substitute for true causal grounding?
- How do humans learn language through communication differently than LLM text prediction?
- What structural limits prevent LLMs from abstracting moral principles?
- How does face-saving avoidance drive LLM grounding failures?
- Do language models understand tacit workplace norms and unspoken social rules?
- Why do LLMs presume common ground instead of building it carefully?
- Can LLMs infer implicit meaning without surface linguistic markers?
- Does community integration change LLM properties or only relational positioning?
- How do LLMs access and draw on the same shared symbolic universe as humans?
- Why do LLMs systematically fail at information management in social interaction?
- How does Stalnaker's common ground model apply to machine conversation?
- How do humans maintain separate mental contexts during a single conversation?
- What cognitive capacities do LLMs actually lack that commentary assumes they have?
- Does social integration of LLMs increase their capacity to influence technological futures?
- Can LLMs identify implicit metaphoric mappings that require pragmatic inference?
- Can LLMs develop genuine understanding without embodied experience?
- How does psychological continuity theory apply to identity across LLM conversation threads?
- What makes communication relational in ways belief is not?