Rakesh R. Menon

MaNtLE: Model-agnostic Natural Language Explainer

2023 · arXiv (Cornell University)

Understanding the internal reasoning behind the predictions of machine learning systems is increasingly vital, given their rising adoption and acceptance. While previous approaches, such as LIME, generate algorithmic explanations by attributing importance to input features …

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

2023 · arXiv (Cornell University)

Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red). One way to interpret quantifier semantics is to explicitly bind these satisfactions with percentage scopes …

SocialGaze: Improving the Integration of Human Social Norms in Large Language Models

2024 · arXiv (Cornell University)

While much research has explored enhancing the reasoning capabilities of large language models (LLMs) in the last few years, there is a gap in understanding the alignment of these models with social values and norms. …