Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Kumar, Sricharan"'
Large language models (LLMs) are proficient in capturing factual knowledge across various domains. However, refining their capabilities on previously seen knowledge or integrating new knowledge from external sources remains a significant challenge. I
Externí odkaz:
http://arxiv.org/abs/2410.09629
Autor:
Li, Zhuohang, Zhang, Jiaxin, Yan, Chao, Das, Kamalika, Kumar, Sricharan, Kantarcioglu, Murat, Malin, Bradley A.
Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowledge corpus to complement the parametric knowledge in LMs provides a ta
Externí odkaz:
http://arxiv.org/abs/2410.08320
Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems. In this study, we introduce a novel and efficient method for deterministic uncertainty estimation called Discriminant Distance-Awarene
Externí odkaz:
http://arxiv.org/abs/2402.12664
Autor:
Cui, Wendi, Zhang, Jiaxin, Li, Zhuohang, Sun, Hao, Lopez, Damien, Das, Kamalika, Malin, Bradley, Kumar, Sricharan
Crafting an ideal prompt for Large Language Models (LLMs) is a challenging task that demands significant resources and expert human input. Existing work treats the optimization of prompt instruction and in-context learning examples as distinct proble
Externí odkaz:
http://arxiv.org/abs/2402.11347
Autor:
Cui, Wendi, Zhang, Jiaxin, Li, Zhuohang, Damien, Lopez, Das, Kamalika, Malin, Bradley, Kumar, Sricharan
Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity, often fail t
Externí odkaz:
http://arxiv.org/abs/2401.02132
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence. However, most existing document enhancement methods require supervised data
Externí odkaz:
http://arxiv.org/abs/2311.09625
Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two types of hallu
Externí odkaz:
http://arxiv.org/abs/2311.01740
Large language models (LLMs) have demonstrated remarkable capabilities in various tasks. However, their suitability for domain-specific tasks, is limited due to their immense scale at deployment, susceptibility to misinformation, and more importantly
Externí odkaz:
http://arxiv.org/abs/2310.20153
Autor:
Berglind, Frej, Temam, Haron, Mukhopadhyay, Supratik, Das, Kamalika, Sajol, Md Saiful Islam, Kumar, Sricharan, Kallurupalli, Kumar
Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning. We present XOOD: a novel extreme value-based OOD detection framework for image classification that consists of two algorithms. The first,
Externí odkaz:
http://arxiv.org/abs/2208.00629
Publikováno v:
IEEE Transactions on Information Theory. 67:5963-5996
Mutual information is a measure of the dependence between random variables that has been used successfully in myriad applications in many fields. Generalized mutual information measures that go beyond classical Shannon mutual information have also re