Zobrazeno 1 - 10
of 520
pro vyhledávání: '"MCCALLUM, ANDREW"'
Autor:
Mysore, Sheshera, Dhanania, Garima, Patil, Kishor, Kallumadi, Surya, McCallum, Andrew, Zamani, Hamed
Personalized search represents a problem where retrieval models condition on historical user interaction data in order to improve retrieval results. However, personalization is commonly perceived as opaque and not amenable to control by users. Furthe
Externí odkaz:
http://arxiv.org/abs/2411.02790
Autor:
Monath, Nicholas, Grathwohl, Will, Boratko, Michael, Fergus, Rob, McCallum, Andrew, Zaheer, Manzil
In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval). Significant
Externí odkaz:
http://arxiv.org/abs/2409.01890
Autor:
Godbole, Ameya, Monath, Nicholas, Kim, Seungyeon, Rawat, Ankit Singh, McCallum, Andrew, Zaheer, Manzil
In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametr
Externí odkaz:
http://arxiv.org/abs/2408.10490
Autor:
Dhanania, Garima, Mysore, Sheshera, Pham, Chau Minh, Iyyer, Mohit, Zamani, Hamed, McCallum, Andrew
Topic models are widely used to analyze document collections. While they are valuable for discovering latent topics in a corpus when analysts are unfamiliar with the corpus, analysts also commonly start with an understanding of the content present in
Externí odkaz:
http://arxiv.org/abs/2406.19928
Autor:
Cheng, Qi, Boratko, Michael, Yelugam, Pranay Kumar, O'Gorman, Tim, Singh, Nalini, McCallum, Andrew, Li, Xiang Lorraine
Large language models have demonstrated impressive performance on commonsense tasks; however, these tasks are often posed as multiple-choice questions, allowing models to exploit systematic biases. Commonsense is also inherently probabilistic with mu
Externí odkaz:
http://arxiv.org/abs/2406.04145
A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on this small su
Externí odkaz:
http://arxiv.org/abs/2405.12801
Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than embedding-based models (dual-encoders) at estimating query-item relevance. Existing approaches perform k-NN search with CE by approximating t
Externí odkaz:
http://arxiv.org/abs/2405.03651
Autor:
Chowdhury, Somnath Basu Roy, Monath, Nicholas, Dubey, Avinava, Zaheer, Manzil, McCallum, Andrew, Ahmed, Amr, Chaturvedi, Snigdha
Extractive opinion summarization involves automatically producing a summary of text about an entity (e.g., a product's reviews) by extracting representative sentences that capture prevalent opinions in the review set. Typically, in online marketplace
Externí odkaz:
http://arxiv.org/abs/2401.08047
Autor:
Angell, Rico, McCallum, Andrew
While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However, these methods achieve scalability at the cost of a
Externí odkaz:
http://arxiv.org/abs/2312.11801
Autor:
Zhao, Jiachen, Zhao, Wenlong, Drozdov, Andrew, Rozonoyer, Benjamin, Sultan, Md Arafat, Lee, Jay-Yoon, Iyyer, Mohit, McCallum, Andrew
We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs) exhibit room for improvement. In this paper, we present the discovery
Externí odkaz:
http://arxiv.org/abs/2311.08640