Zobrazeno 1 - 10
of 13 808
pro vyhledávání: '"Khattab IS"'
Autor:
Jacob, Mathew, Lindgren, Erik, Zaharia, Matei, Carbin, Michael, Khattab, Omar, Drozdov, Andrew
Rerankers, typically cross-encoders, are often used to re-score the documents retrieved by cheaper initial IR systems. This is because, though expensive, rerankers are assumed to be more effective. We challenge this assumption by measuring reranker p
Externí odkaz:
http://arxiv.org/abs/2411.11767
Many open-ended conversations (e.g., tutoring lessons or business meetings) revolve around pre-defined reference materials, like worksheets or meeting bullets. To provide a framework for studying such conversation structure, we introduce Problem-Orie
Externí odkaz:
http://arxiv.org/abs/2411.07598
The hallucinations of large language models (LLMs) are increasingly mitigated by allowing LLMs to search for information and to ground their answers in real sources. Unfortunately, LLMs often struggle with posing the right search queries, especially
Externí odkaz:
http://arxiv.org/abs/2410.23214
Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can host locally are often less cap
Externí odkaz:
http://arxiv.org/abs/2410.17127
In recent years, interest in vision-language tasks has grown, especially those involving chart interactions. These tasks are inherently multimodal, requiring models to process chart images, accompanying text, underlying data tables, and often user qu
Externí odkaz:
http://arxiv.org/abs/2410.13883
Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt template.
Externí odkaz:
http://arxiv.org/abs/2407.10930
Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent inductive biase
Externí odkaz:
http://arxiv.org/abs/2407.07516
Autor:
Xian, Jasper, Samuel, Saron, Khoubsirat, Faraz, Pradeep, Ronak, Sultan, Md Arafat, Florian, Radu, Roukos, Salim, Sil, Avirup, Potts, Christopher, Khattab, Omar
We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels. The method depends on generating synthetic queries for documents using a language model (LM), and the key
Externí odkaz:
http://arxiv.org/abs/2406.11706
Autor:
Opsahl-Ong, Krista, Ryan, Michael J, Purtell, Josh, Broman, David, Potts, Christopher, Zaharia, Matei, Khattab, Omar
Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study prompt optimization for LM progra
Externí odkaz:
http://arxiv.org/abs/2406.11695
Many online content portals allow users to ask questions to supplement their understanding (e.g., of lectures). While information retrieval (IR) systems may provide answers for such user queries, they do not directly assist content creators -- such a
Externí odkaz:
http://arxiv.org/abs/2403.03956