22 citations · 25 across the 10 of their papers we have counts for
11 papers
BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval
Eylon Caplan, Shamik Roy, Shib Sankar Dasgupta +2
Open-ended queries in modern Retrieval-Augmented Generation (RAG) are increasingly "diffuse," requiring a large set of documents to be assembled into a finite LLM context window. T…
PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts
Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum +1
To discover the weaknesses of LLMs, researchers often embed prompts into a vector space and cluster them to extract insightful patterns. However, vector embeddings primarily captur…
A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
Shib Dasgupta, Michael Boratko, Andrew McCallum
Personalized item recommendation typically suffers from data sparsity, which is most often addressed by learning vector representations of users and items via low-rank matrix facto…
HITgram: A Platform for Experimenting with n-gram Language Models
Shibaranjani Dasgupta, Chandan Maity, Somdip Mukherjee +3
Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimenta…
Answering Compositional Queries with Set-Theoretic Embeddings
Shib Dasgupta, Andrew McCallum, Steffen Rendle +1
The need to compactly and robustly represent item-attribute relations arises in many important tasks, such as faceted browsing and recommendation systems. A popular machine learnin…
Box Embeddings: An open-source library for representation learning using geometric structures
Tejas Chheda, Purujit Goyal, Trang Tran +4
A major factor contributing to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with geometric structures (eg. d…
Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings
Shib Sankar Dasgupta, Michael Boratko, Siddhartha Mishra +4
Learning representations of words in a continuous space is perhaps the most fundamental task in NLP, however words interact in ways much richer than vector dot product similarity c…
Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
Xuelu Chen, Michael Boratko, Muhao Chen +3
Knowledge bases often consist of facts which are harvested from a variety of sources, many of which are noisy and some of which conflict, resulting in a level of uncertainty for ea…
Improving Local Identifiability in Probabilistic Box Embeddings
Shib Sankar Dasgupta, Michael Boratko, Dongxu Zhang +3
Geometric embeddings have recently received attention for their natural ability to represent transitive asymmetric relations via containment. Box embeddings, where objects are repr…
Dating Documents using Graph Convolution Networks
Shikhar Vashishth, Shib Sankar Dasgupta, Swayambhu Nath Ray +1
Document date is essential for many important tasks, such as document retrieval, summarization, event detection, etc. While existing approaches for these tasks assume accurate know…
AD3: Attentive Deep Document Dater
Swayambhu Nath Ray, Shib Sankar Dasgupta, Partha Talukdar
Knowledge of the creation date of documents facilitates several tasks such as summarization, event extraction, temporally focused information extraction etc. Unfortunately, for mos…