no code implementations • 4 Apr 2024 • Dongwei Jiang, Jingyu Zhang, Orion Weller, Nathaniel Weir, Benjamin Van Durme, Daniel Khashabi
Can LLMs continually improve their previous outputs for better results?
2 code implementations • 22 Mar 2024 • Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, Luca Soldaini
We introduce our dataset FollowIR, which contains a rigorous instruction evaluation benchmark as well as a training set for helping IR models learn to better follow real-world instructions.
no code implementations • 19 Mar 2024 • Jeffrey Cheng, Marc Marone, Orion Weller, Dawn Lawrie, Daniel Khashabi, Benjamin Van Durme
Using this analysis, we find that effective cutoffs often differ from reported cutoffs.
no code implementations • 22 Feb 2024 • Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Jiang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Jansen, Peter Clark, Benjamin Van Durme
Contemporary language models enable new opportunities for structured reasoning with text, such as the construction and evaluation of intuitive, proof-like textual entailment trees without relying on brittle formal logic.
no code implementations • 15 Sep 2023 • Orion Weller, Kyle Lo, David Wadden, Dawn Lawrie, Benjamin Van Durme, Arman Cohan, Luca Soldaini
Using large language models (LMs) for query or document expansion can improve generalization in information retrieval.
no code implementations • 13 Jul 2023 • Samuel Barham, Orion Weller, Michelle Yuan, Kenton Murray, Mahsa Yarmohammadi, Zhengping Jiang, Siddharth Vashishtha, Alexander Martin, Anqi Liu, Aaron Steven White, Jordan Boyd-Graber, Benjamin Van Durme
To foster the development of new models for collaborative AI-assisted report generation, we introduce MegaWika, consisting of 13 million Wikipedia articles in 50 diverse languages, along with their 71 million referenced source materials.
no code implementations • 22 May 2023 • Orion Weller, Marc Marone, Nathaniel Weir, Dawn Lawrie, Daniel Khashabi, Benjamin Van Durme
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data.
1 code implementation • 12 May 2023 • Orion Weller, Dawn Lawrie, Benjamin Van Durme
Although the Information Retrieval (IR) community has adopted LMs as the backbone of modern IR architectures, there has been little to no research in understanding how negation impacts neural IR.
no code implementations • 29 Apr 2023 • James Mayfield, Eugene Yang, Dawn Lawrie, Samuel Barham, Orion Weller, Marc Mason, Suraj Nair, Scott Miller
By repeating this process, collections of arbitrary size can be created in the style of MS MARCO but using naturally-occurring documents in any desired genre and domain of discourse.
no code implementations • 20 Dec 2022 • Kangda Wei, Dawn Lawrie, Benjamin Van Durme, Yunmo Chen, Orion Weller
Answering complex questions often requires multi-step reasoning in order to obtain the final answer.
no code implementations • 20 Dec 2022 • Orion Weller, Aleem Khan, Nathaniel Weir, Dawn Lawrie, Benjamin Van Durme
Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems.
1 code implementation • NAACL 2022 • Orion Weller, Marc Marone, Vladimir Braverman, Dawn Lawrie, Benjamin Van Durme
Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks.
1 code implementation • ACL 2022 • Orion Weller, Kevin Seppi, Matt Gardner
We find that there is a simple heuristic for when to use one of these techniques over the other: pairwise MTL is better than STILTs when the target task has fewer instances than the supporting task and vice versa.
2 code implementations • Findings (ACL) 2022 • Orion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan, Christian Gollan, Dominic Telaar, Matthias Paulik
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages.
1 code implementation • NAACL 2021 • Wilson Fearn, Orion Weller, Kevin Seppi
Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis.
no code implementations • EACL 2021 • Orion Weller, Matthias Sperber, Christian Gollan, Joris Kluivers
However, all previous work has only looked at this problem from the consecutive perspective, leaving uncertainty on whether these approaches are effective in the more challenging streaming setting.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • EMNLP 2020 • Orion Weller, Nicholas Lourie, Matt Gardner, Matthew E. Peters
Typically, machine learning systems solve new tasks by training on thousands of examples.
no code implementations • WS 2020 • Orion Weller, Nancy Fulda, Kevin Seppi
Understanding and identifying humor has been increasingly popular, as seen by the number of datasets created to study humor.
no code implementations • ACL 2020 • Orion Weller, Hildebr, Jordan t, Ilya Reznik, Christopher Challis, E. Shannon Tass, Quinn Snell, Kevin Seppi
Predicting reading time has been a subject of much previous work, focusing on how different words affect human processing, measured by reading time.
no code implementations • LREC 2020 • Orion Weller, Kevin Seppi
We also introduce this dataset as a task for future work, where models learn to predict the level of humor in a joke.
2 code implementations • IJCNLP 2019 • Orion Weller, Kevin Seppi
These experiments show that this method outperforms all previous work done on these tasks, with an F-measure of 93. 1% for the Puns dataset and 98. 6% on the Short Jokes dataset.