Stalnaker’s common ground is not a score. It is a state: the set of propositions that participants in a conversation take to be shared, and that they treat as available for presupposition and reference. A dialogue model can produce a fluent next turn without updating that state correctly. The useful question is therefore not whether …
Continue reading What Do We Both Know? Stalnaker’s Common Ground as a Test for Dialogue Models
Author:Terri Lane
Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack
Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack Read the following continuation of a short narrative prompt. Nothing is obviously broken at the sentence level — the grammar is clean, the register holds, the transitions read smoothly if you only look at adjacent sentences: Prompt: …
Continue reading Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack
How Language Models Handle Ambiguity and Why It Matters
Ambiguity is a property of natural language in which a single surface form can correspond to multiple underlying structures or meanings. In morphosyntactic terms, this includes lexical ambiguity, structural ambiguity, and scope ambiguity. For transformer language models, ambiguity is not a peripheral edge case; it is a central test of whether a model has acquired …
Continue reading How Language Models Handle Ambiguity and Why It Matters
The Relationship Between Grammar and Meaning in Neural Networks
Grammar and meaning are usually treated as separate layers of language. One is a system of formal rules; the other is a network of concepts and referents. In transformer language models, that separation gets harder to hold onto. A model that predicts the next token has to learn something about agreement, word order, and argument …
Continue reading The Relationship Between Grammar and Meaning in Neural Networks
Why Narrative Coherence in Language Models Is Not Story Understanding
Ask a language model to write a short story. You will get something that reads like one. A protagonist, a conflict, a turning point, a resolution. Grammatical prose. Emotional shifts at the moments you would expect. Skim it and you might not notice anything wrong. That is exactly the problem. What looks like storytelling is, …
Continue reading Why Narrative Coherence in Language Models Is Not Story Understanding