3 papers
cs.SI2025
Extending the BEND Framework to Webgraphs
Evan M. Williams, Peter Carragher, Kyle Herdrich +2
Attempts to manipulate webgraphs can have many downstream impacts, but analysts lack shared quantitative metrics to characterize actions taken to manipulate information environment…
cs.CV2025
SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
Peter Carragher, Nikitha Rao, Abhinand Jha +2
Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts, impeding their deployment in in…
cs.LG2025
Quantifying Memorization and Parametric Response Rates in Retrieval-Augmented Vision-Language Models
Peter Carragher, Abhinand Jha, R Raghav +1
Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underd…