Retrieval-augmented generation for large language models: A survey
Y Gao, Y Xiong, X Gao, K Jia, J Pan, Y Bi, Y Dai… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) demonstrate powerful capabilities, but they still face
challenges in practical applications, such as hallucinations, slow knowledge updates, and …
challenges in practical applications, such as hallucinations, slow knowledge updates, and …
Survey of hallucination in natural language generation
Natural Language Generation (NLG) has improved exponentially in recent years thanks to
the development of sequence-to-sequence deep learning technologies such as Transformer …
the development of sequence-to-sequence deep learning technologies such as Transformer …
Direct preference optimization: Your language model is secretly a reward model
While large-scale unsupervised language models (LMs) learn broad world knowledge and
some reasoning skills, achieving precise control of their behavior is difficult due to the …
some reasoning skills, achieving precise control of their behavior is difficult due to the …
Coderl: Mastering code generation through pretrained models and deep reinforcement learning
Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …
specification. Recent approaches using large-scale pretrained language models (LMs) have …
Fine-tuning language models to find agreement among humans with diverse preferences
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with
the preferences of a prototypical user. This work assumes that human preferences are static …
the preferences of a prototypical user. This work assumes that human preferences are static …
Unified structure generation for universal information extraction
Information extraction suffers from its varying targets, heterogeneous structures, and
demand-specific schemas. In this paper, we propose a unified text-to-structure generation …
demand-specific schemas. In this paper, we propose a unified text-to-structure generation …
Semantic communications for future internet: Fundamentals, applications, and challenges
With the increasing demand for intelligent services, the sixth-generation (6G) wireless
networks will shift from a traditional architecture that focuses solely on a high transmission …
networks will shift from a traditional architecture that focuses solely on a high transmission …
Cascaded diffusion models for high fidelity image generation
We show that cascaded diffusion models are capable of generating high fidelity images on
the class-conditional ImageNet generation benchmark, without any assistance from auxiliary …
the class-conditional ImageNet generation benchmark, without any assistance from auxiliary …
Contrastive decoding: Open-ended text generation as optimization
Given a language model (LM), maximum probability is a poor decoding objective for open-
ended generation, because it produces short and repetitive text. On the other hand …
ended generation, because it produces short and repetitive text. On the other hand …
From show to tell: A survey on deep learning-based image captioning
Connecting Vision and Language plays an essential role in Generative Intelligence. For this
reason, large research efforts have been devoted to image captioning, ie describing images …
reason, large research efforts have been devoted to image captioning, ie describing images …