6 papers
Lightweight Latent Reasoning for Narrative Tasks
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a que…
MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents
Alexander Gurung, Spandana Gella, Alexandre Drouin +3
Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive in…
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
Miao Li, Irina Saparina, Alexander Gurung +1
Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using…
SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific Articles
Miao Li, Alexander Gurung, Irina Saparina +1
We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (LLMs). Existing long-context dat…
Learning to Reason for Long-Form Story Generation
Alexander Gurung, Mirella Lapata
Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engag…
CHIRON: Rich Character Representations in Long-Form Narratives
Alexander Gurung, Mirella Lapata
Characters are integral to long-form narratives, but are poorly understood by existing story analysis and generation systems. While prior work has simplified characters via graph-b…