Shashank Srivastava
6 papers in the PaperMetrix corpus
Papers by this author
-
Learning to Ask for Conversational Machine Learning
2019
Shashank Srivastava, Igor Labutov, Tom Mitchell. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
-
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. …
-
Algorithmic Improvements to List Decoding of Folded Reed-Solomon Codes
2026 · Society for Industrial and Applied Mathematics eBooks
Folded Reed-Solomon (FRS) codes are a well-studied family of codes, known for achieving list decoding capacity. In this work, we give improved deterministic and randomized algorithms for list decoding FRS codes of rate \(R\) up …
-
Joint Concept Learning and Semantic Parsing from Natural Language Explanations
2017
Natural language constitutes a predominant medium for much of human learning and pedagogy. We consider the problem of concept learning from natural language explanations, and a small number of labeled examples of the concept. For …