Zobrazeno 1 - 10
of 328
pro vyhledávání: '"Guo, Jiafeng"'
Autor:
Zuo, Yuxin, Jiang, Wenxuan, Liu, Wenxuan, Li, Zixuan, Bai, Long, Wang, Hanbin, Zeng, Yutao, Jin, Xiaolong, Guo, Jiafeng, Cheng, Xueqi
Empirical evidence suggests that LLMs exhibit spontaneous cross-lingual alignment. Our findings suggest that although LLMs also demonstrate promising cross-lingual alignment in Information Extraction, there remains significant imbalance across langua
Externí odkaz:
http://arxiv.org/abs/2411.04794
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essent
Externí odkaz:
http://arxiv.org/abs/2410.23091
The advancement of LLMs has significantly boosted the performance of complex long-form question answering tasks. However, one prominent issue of LLMs is the generated "hallucination" responses that are not factual. Consequently, attribution for each
Externí odkaz:
http://arxiv.org/abs/2410.12558
Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG in combatin
Externí odkaz:
http://arxiv.org/abs/2410.11217
Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches are limit
Externí odkaz:
http://arxiv.org/abs/2409.18409
Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it is that a R
Externí odkaz:
http://arxiv.org/abs/2409.16146
As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency poses challenges to scientific evaluation and ethical deployment. Rec
Externí odkaz:
http://arxiv.org/abs/2409.14781
Non-Factoid (NF) Question Answering (QA) is challenging to evaluate due to diverse potential answers and no objective criterion. The commonly used automatic evaluation metrics like ROUGE or BERTScore cannot accurately measure semantic similarities or
Externí odkaz:
http://arxiv.org/abs/2409.14744
Generative LLM have achieved significant success in various industrial tasks and can effectively adapt to vertical domains and downstream tasks through ICL. However, with tasks becoming increasingly complex, the context length required by ICL is also
Externí odkaz:
http://arxiv.org/abs/2408.10497
Unbiased Learning to Rank (ULTR) aims to leverage biased implicit user feedback (e.g., click) to optimize an unbiased ranking model. The effectiveness of the existing ULTR methods has primarily been validated on synthetic datasets. However, their per
Externí odkaz:
http://arxiv.org/abs/2408.09817