We have 4 of 19 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Intent drift is established as a measurable multi-turn failure mode and explicit state maintenance as a partial mitigation and IntentFlux is introduced, an executable benchmark that converts verifiable tasks into dialogues with controlled intent changes while preserving their original graders.
As LLMs become increasingly capable of completing tasks for users, a central concern is that everyday AI use may become primarily cognitive offloading, eroding the opportunities through which people develop their own capabilities. We analyse large-scale human-LLM conversations to ask whether informal learning behaviors...
This work presents TACT (Taxonomy-Aligned Conversational Tutor), a human-grounded framework for post-training and evaluating pedagogically adaptive ESL tutors and develops two complementary taxonomies: the Tutor-Strategy Taxonomy with 13 tutor response strategies and the Student-Move Taxonomy characterizing learner beh...
WILDTRACE is introduced, a benchmark of 481 tasks over 214 naturally occurring long-form sources such as technical incident reports and lesser-known literary narratives, where all evidence trails arise from the document's own causal, temporal, and narrative logic.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
