7 accepted papers
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
Computer vision models can be explained by attributing the output decision to the input pixels. While effective methods for explaining convolutional neural networks have been proposed, these methods often produce low-quality attributions when applied to vision transformers (ViTs). State-of-the-art m…
Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a grounding of atomic propositions (APs) phase and a translation phase. However, existing m…
Attribution algorithms explain computer vision models by attributing the model response to pixels within the input. Existing attribution methods generate explanations by combining transformations of internal model representations such as class activation maps, gradients, attention, or relevance scor…
Neural SDEs with Brownian motion as noise lead to smoother attributions than traditional ResNets. Various attribution methods such as saliency maps, integrated gradients, DeepSHAP and DeepLIFT have been shown to be more robust for neural SDEs than for ResNets using the recently proposed sensitivity…