2 papers
cs.LG2026
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Julian Skirzynski, Harry Cheon, Shreyas Kadekodi +2
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few data…
cs.CL2025
Quantifying Cognitive Bias Induction in LLM-Generated Content
Abeer Alessa, Param Somane, Akshaya Lakshminarasimhan +3
Large language models (LLMs) are integrated into applications like shopping reviews, summarization, or medical diagnosis support, where their use affects human decisions. We invest…