8 papers
Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages
Nick McKenna, Xinnuo Xu, Jack Williams +3
A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python compared to Excel. Typical train…
From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output
Advait Sarkar, Christian Poelitz, Viktor Kewenig
Generative AI tools often answer questions using source documents, e.g., through retrieval augmented generation. Current groundedness and hallucination evaluations largely frame th…
A Benchmark to Assess Common Ground in Human-AI Collaboration
Christian Poelitz, Finale Doshi-Velez, Siân Lindley
AI is becoming increasingly integrated into everyday life, both in professional work environments and in leisure and entertainment contexts. This integration requires AI to move be…
An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking
Ahana Ghosh, Advait Sarkar, Siân Lindley +1
Generative AI (GenAI) tools improve productivity in knowledge workflows such as writing, but also risk overreliance and reduced critical thinking. Cognitive forcing functions (CFFs…
Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach
Christian Poelitz, Nick McKenna
Real dialogues with AI assistants for solving data-centric tasks often follow dynamic, unpredictable paths due to imperfect information provided by the user or in the data, which m…
MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL
Arian Askari, Christian Poelitz, Xinye Tang
Self-correction in text-to-SQL is the process of prompting large language model (LLM) to revise its previously incorrectly generated SQL, and commonly relies on manually crafted se…