Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Liu, Fangchao"'
Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular solution to enha
Externí odkaz:
http://arxiv.org/abs/2402.01176
Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for the input q
Externí odkaz:
http://arxiv.org/abs/2305.13859
Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application. Few-shot and zero-shot RE are two representative low-shot RE tasks, which seem to be with similar ta
Externí odkaz:
http://arxiv.org/abs/2203.12274
Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the lack of unde
Externí odkaz:
http://arxiv.org/abs/2203.12258
Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervi
Externí odkaz:
http://arxiv.org/abs/2106.09558
Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels using multi-instance learning te
Externí odkaz:
http://arxiv.org/abs/2012.04334