Aditya Pola

Deepika SN Vemuri, Gautham Bellamkonda, Aditya Pola et al.

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring predictions as a linear combination of semantic concepts. However, a linear combination is inherently limiting. So we propose the enhancement of concept-based learning models through propositional logic. We introduce a logic module that is carefully designed to connect the learned concepts from CBMs through differentiable logic operations, such that our proposed LogicCBM can go beyond simple weighted combinations of concepts to leverage various logical operations to yield the final predictions, while maintaining end-to-end learnability. Composing concepts using a set of logic operators enables the model to capture inter-concept relations, while simultaneously improving the expressivity of the model in terms of logic operations. Our empirical studies on well-known benchmarks and synthetic datasets demonstrate that these models have better accuracy, perform effective interventions and are highly interpretable.

Aditya Pola, Vineeth N. Balasubramanian

Following an instruction involves distinct sub-processes, such as reading content, reading the instruction, executing it, and producing an answer. We ask where, along the layer stack, instruction following begins, the point where reading gives way to doing. We introduce three simple datasets (Key-Value, Quote Attribution, Letter Selection) and two hop compositions of these tasks. Using activation patching on minimal-contrast prompt pairs, we measure a layer-wise flip rate that indicates when substituting selected residual activations changes the predicted answer. Across models in the Llama family, we observe an inflection point, which we term onset, where interventions that change predictions before this point become largely ineffective afterward. Multi-hop compositions show a similar onset location. These results provide a simple, replicable way to locate where instruction following begins and to compare this location across tasks and model sizes.