In-Context Learning | Jason S. Lucas

NLP Applications & Reasoning

Fri, 01 Aug 2025 00:00:00 +0000

Advancing language understanding requires pushing beyond standard benchmarks into complex, real-world reasoning tasks. This project explores how in-context learning and graph-based representations can improve AI performance across diverse application domains—from summarizing task-oriented dialogue in conversational AI systems to translating structured database queries into natural language and reasoning over molecular structures for scientific discovery. These efforts contribute foundational NLP methods that support the broader mission of building AI systems capable of robust, generalizable reasoning across languages, domains, and modalities.

Related Publications:

Chain-of-Interactions (CoI) (2025, EMNLP) — Dialogue summarization
Semantic Captioning / SQL2Text (2025, COLING) — Graph-aware few-shot ICL
Graph-based Molecular ICL (GAMIC) (2025, EMNLP) — Molecular reasoning with Morgan fingerprints

Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text

Sat, 01 Feb 2025 00:00:00 +0000

Note

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Note

Dataset and codes are accessible for research use.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including .

Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation

Tue, 05 Dec 2023 00:00:00 +0000

Note

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Note

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including .