Alert button
Picture for Andrew McCallum

Andrew McCallum

Alert button

Incremental Extractive Opinion Summarization Using Cover Trees

Jan 16, 2024
Somnath Basu Roy Chowdhury, Nicholas Monath, Avinava Dubey, Manzil Zaheer, Andrew McCallum, Amr Ahmed, Snigdha Chaturvedi

Viaarxiv icon

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching

Dec 19, 2023
Rico Angell, Andrew McCallum

Viaarxiv icon

Multistage Collaborative Knowledge Distillation from Large Language Models

Nov 15, 2023
Jiachen Zhao, Wenlong Zhao, Andrew Drozdov, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, Andrew McCallum

Figure 1 for Multistage Collaborative Knowledge Distillation from Large Language Models
Figure 2 for Multistage Collaborative Knowledge Distillation from Large Language Models
Figure 3 for Multistage Collaborative Knowledge Distillation from Large Language Models
Figure 4 for Multistage Collaborative Knowledge Distillation from Large Language Models
Viaarxiv icon

PaRaDe: Passage Ranking using Demonstrations with Large Language Models

Oct 22, 2023
Andrew Drozdov, Honglei Zhuang, Zhuyun Dai, Zhen Qin, Razieh Rahimi, Xuanhui Wang, Dana Alon, Mohit Iyyer, Andrew McCallum, Donald Metzler, Kai Hui

Figure 1 for PaRaDe: Passage Ranking using Demonstrations with Large Language Models
Figure 2 for PaRaDe: Passage Ranking using Demonstrations with Large Language Models
Figure 3 for PaRaDe: Passage Ranking using Demonstrations with Large Language Models
Figure 4 for PaRaDe: Passage Ranking using Demonstrations with Large Language Models
Viaarxiv icon

To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders

Oct 21, 2023
Haw-Shiuan Chang, Nikhil Agarwal, Andrew McCallum

Viaarxiv icon

Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens

Sep 08, 2023
Ronald Seoh, Haw-Shiuan Chang, Andrew McCallum

Figure 1 for Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
Figure 2 for Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
Figure 3 for Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
Figure 4 for Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
Viaarxiv icon

Answering Compositional Queries with Set-Theoretic Embeddings

Jun 07, 2023
Shib Dasgupta, Andrew McCallum, Steffen Rendle, Li Zhang

Figure 1 for Answering Compositional Queries with Set-Theoretic Embeddings
Figure 2 for Answering Compositional Queries with Set-Theoretic Embeddings
Figure 3 for Answering Compositional Queries with Set-Theoretic Embeddings
Figure 4 for Answering Compositional Queries with Set-Theoretic Embeddings
Viaarxiv icon

Large Language Model Augmented Narrative Driven Recommendations

Jun 04, 2023
Sheshera Mysore, Andrew McCallum, Hamed Zamani

Figure 1 for Large Language Model Augmented Narrative Driven Recommendations
Figure 2 for Large Language Model Augmented Narrative Driven Recommendations
Figure 3 for Large Language Model Augmented Narrative Driven Recommendations
Figure 4 for Large Language Model Augmented Narrative Driven Recommendations
Viaarxiv icon

Machine Reading Comprehension using Case-based Reasoning

May 24, 2023
Dung Thai, Dhruv Agarwal, Mudit Chaudhary, Rajarshi Das, Manzil Zaheer, Jay-Yoon Lee, Hannaneh Hajishirzi, Andrew McCallum

Figure 1 for Machine Reading Comprehension using Case-based Reasoning
Figure 2 for Machine Reading Comprehension using Case-based Reasoning
Figure 3 for Machine Reading Comprehension using Case-based Reasoning
Figure 4 for Machine Reading Comprehension using Case-based Reasoning
Viaarxiv icon

Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond

May 20, 2023
Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, Andrew McCallum

Figure 1 for Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Figure 2 for Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Figure 3 for Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Figure 4 for Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Viaarxiv icon