Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Arık, Sercan Ö."'
Retrieval-Augmented Generation (RAG), while effective in integrating external knowledge to address the limitations of large language models (LLMs), can be undermined by imperfect retrieval, which may introduce irrelevant, misleading, or even maliciou
Externí odkaz:
http://arxiv.org/abs/2410.07176
Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by Retrieval-Augmented
Externí odkaz:
http://arxiv.org/abs/2406.02818
Large language models (LLMs) aligned through reinforcement learning from human feedback (RLHF) have quickly become one of the dominant paradigms for building intelligent conversational assistant agents. However, despite their strong performance acros
Externí odkaz:
http://arxiv.org/abs/2406.00222
Autor:
Sarkar, Pritam, Ebrahimi, Sayna, Etemad, Ali, Beirami, Ahmad, Arık, Sercan Ö., Pfister, Tomas
Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is generated ab
Externí odkaz:
http://arxiv.org/abs/2405.18654
Large language models (LLMs) have achieved remarkable advancements in natural language understanding and generation. However, one major issue towards their widespread deployment in the real world is that they can generate "hallucinated" answers that
Externí odkaz:
http://arxiv.org/abs/2311.09533
Autor:
Sun, Ruoxi, Arik, Sercan Ö., Sinha, Rajarishi, Nakhost, Hootan, Dai, Hanjun, Yin, Pengcheng, Pfister, Tomas
Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose "SQLPrompt", tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs)
Externí odkaz:
http://arxiv.org/abs/2311.02883
Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials (RCTs) suffer from high cost or impracticality. For
Externí odkaz:
http://arxiv.org/abs/2311.00886
Autor:
Sun, Ruoxi, Arik, Sercan Ö., Muzio, Alex, Miculicich, Lesly, Gundabathula, Satya, Yin, Pengcheng, Dai, Hanjun, Nakhost, Hootan, Sinha, Rajarishi, Wang, Zifeng, Pfister, Tomas
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data. This paper introduces t
Externí odkaz:
http://arxiv.org/abs/2306.00739
Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on t
Externí odkaz:
http://arxiv.org/abs/2210.03675
Self-supervised learning allows AI systems to learn effective representations from large amounts of data using tasks that do not require costly labeling. Mode collapse, i.e., the model producing identical representations for all inputs, is a central
Externí odkaz:
http://arxiv.org/abs/2209.07999