4 papers
No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation
Yufei Tao, Ameeta Agrawal
Large language models (LLMs) can answer questions and summarize documents when conditioned on external contexts (e.g., retrieved evidence), yet context use remains unreliable: mode…
CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences
Rhitabrat Pokharel, Yufei Tao, Ameeta Agrawal
Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs.…
"Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Models
Yufei Tao, Adam Hiatt, Rahul Seetharaman +1
Large language models are capable of leveraging both contextual and parametric knowledge but how they prioritize and integrate these sources remains underexplored. We introduce CoP…
When Context Leads but Parametric Memory Follows in Large Language Models
Yufei Tao, Adam Hiatt, Erik Haake +2
Large language models (LLMs) have demonstrated remarkable progress in leveraging diverse knowledge sources. This study investigates how nine widely used LLMs allocate knowledge bet…