Zobrazeno 1 - 10
of 508
pro vyhledávání: '"Zhou, Ben"'
Retrieval Augmented Generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieval from external sources. However, it often struggles to filter out inconsistent and irrelevant information th
Externí odkaz:
http://arxiv.org/abs/2409.12468
Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this observation, and propose label-ag
Externí odkaz:
http://arxiv.org/abs/2406.11243
Large language models primarily rely on inductive reasoning for decision making. This results in unreliable decisions when applied to real-world tasks that often present incomplete contexts and conditions. Thus, accurate probability estimation and ap
Externí odkaz:
http://arxiv.org/abs/2404.12494
Autor:
Zhou, Ben, Zhang, Hongming, Chen, Sihao, Yu, Dian, Wang, Hongwei, Peng, Baolin, Roth, Dan, Yu, Dong
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In this work,
Externí odkaz:
http://arxiv.org/abs/2404.00205
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after safety align
Externí odkaz:
http://arxiv.org/abs/2311.09827
Despite the recent advancement in large language models (LLMs) and their high performances across numerous benchmarks, recent research has unveiled that LLMs suffer from hallucinations and unfaithful reasoning. This work studies a specific type of ha
Externí odkaz:
http://arxiv.org/abs/2311.09702
Autor:
Chen, Sihao, Zhang, Hongming, Chen, Tong, Zhou, Ben, Yu, Wenhao, Yu, Dian, Peng, Baolin, Wang, Hongwei, Roth, Dan, Yu, Dong
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence of text is
Externí odkaz:
http://arxiv.org/abs/2311.04335
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In recent work
Externí odkaz:
http://arxiv.org/abs/2308.04756
Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end models prevents them from being interpretable to humans, undermining trust
Externí odkaz:
http://arxiv.org/abs/2305.14882
Publikováno v:
Proceedings of ACL 2023
Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems' generalizability due to existing datasets' limi
Externí odkaz:
http://arxiv.org/abs/2212.10467