12 papers
ISEE: Interactive Semantic Enrichment for Database Fields
Yuan Tian, Yiru Chen, Rakesh R. Menon +8
LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their performance heavily depends on the…
TACO: Task-Aware Column Description Generation Using LLMs
Ting Cai, Rakesh R. Menon, Yiru Chen +8
Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks…
INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models
Aum Kendapadi, Kerem Zaman, Rakesh R. Menon +1
Large language models (LLMs) excel at answering questions but remain passive learners-absorbing static data without the ability to question and refine knowledge. This paper explore…
DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers
Rakesh R. Menon, Shashank Srivastava
Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain cl…
SocialGaze: Improving the Integration of Human Social Norms in Large Language Models
Anvesh Rao Vijjini, Rakesh R. Menon, Jiayi Fu +2
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…
Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers
Kangda Wei, Sayan Ghosh, Rakesh R. Menon +1
Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instruc…
Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models
Yiyuan Li, Rakesh R. Menon, Sayan Ghosh +1
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 semantic…
MaNtLE: Model-agnostic Natural Language Explainer
Rakesh R. Menon, Kerem Zaman, Shashank Srivastava
Understanding the internal reasoning behind the predictions of machine learning systems is increasingly vital, given their rising adoption and acceptance. While previous approaches…
LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning
Sayan Ghosh, Rakesh R Menon, Shashank Srivastava
A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural lan…
CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations
Rakesh R Menon, Sayan Ghosh, Shashank Srivastava
Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from languag…
Improving and Simplifying Pattern Exploiting Training
Derek Tam, Rakesh R Menon, Mohit Bansal +2
Recently, pre-trained language models (LMs) have achieved strong performance when fine-tuned on difficult benchmarks like SuperGLUE. However, performance can suffer when there are…
Shared Learning : Enhancing Reinforcement in -Ensembles
Rakesh R Menon, Balaraman Ravindran
Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. H…