4 papers
Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
Shubhashis Roy Dipta, Francis Ferraro
Recent approaches have shown impressive proficiency in extracting and leveraging parametric knowledge from Large-Language Models (LLMs) and Vision-Language Models (VLMs). In this w…
TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
Maithili Kadam, Francis Ferraro
Large language models (LLMs) excel at general language tasks but often struggle with event-based questions-especially those requiring causal or temporal reasoning. We introduce TAG…
If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition
Shubhashis Roy Dipta, Francis Ferraro
Prior work has shown that presupposition in generated questions can introduce unverified assumptions, leading to inconsistencies in claim verification. Additionally, prompt sensiti…
Inductive Bias Extraction and Matching for LLM Prompts
Christian M. Angel, Francis Ferraro
The active research topic of prompt engineering makes it evident that LLMs are sensitive to small changes in prompt wording. A portion of this can be ascribed to the inductive bias…