4 accepted papers
Vision Transformers often rely on spurious background correlations rather than foreground object features. While prior model pruning approaches focus solely on improving accuracy, they lack interpretability and fail to verify whether predictions are actually made by focusing on the main foreground o
Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear approximations that fail to capture the causal and semantic complexit…
Large language models remain vulnerable to jailbreak attacks, inputs crafted to bypass safety mechanisms and elicit harmful responses, despite advances in alignment and instruction tuning. Existing attacks often rely on prompt rewrites, dense optimization, or ad hoc heuristics, and lack interpretabi…
We study concept-level forgetting in pretrained vision models: removing an entire semantic category so the system no longer recognizes that object in unseen images and contexts, rather than merely forgetting specific training examples. Prior work either applies blunt global projections or fine-tunes