相关论文: Handling Open-Vocabulary Constructs in Formalizing…

Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known…

Standard segmentation setups are unable to deliver models that can recognize concepts outside the training taxonomy. Open-vocabulary approaches promise to close this gap through language-image pretraining on billions of image-caption pairs.…

Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually have heavy inference burden or rely on external knowledge,…

Open-vocabulary object detection aims to provide object detectors trained on a fixed set of object categories with the generalizability to detect objects described by arbitrary text queries. Previous methods adopt knowledge distillation to…

Retrieval-augmented generation (RAG) has emerged to address the knowledge-intensive visual question answering (VQA) task. Current methods mainly employ separate retrieval and generation modules to acquire external knowledge and generate…

Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely ``read'' text embedded in images, or do they merely…

Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results. One factor which limits the power of language models in this context is the existence of many specialized domains with…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most…

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…

We propose a rule-based technique to generate redundancy-free NL descriptions of OWL entities.The existing approaches which address the problem of verbalizing OWL ontologies generate NL text segments which are close to their counterpart OWL…

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a…

Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data; yet novel objects occur frequently, necessitating the requirement of sustaining up-to-date object…

While generative models such as Latent Dirichlet Allocation (LDA) have proven fruitful in topic modeling, they often require detailed assumptions and careful specification of hyperparameters. Such model complexity issues only compound when…

Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework…

Prompt tuning is an effective way to adapt the pre-trained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work combines the learnable textual tokens with the class tokens to…

Multi-modal keyphrase prediction (MMKP) aims to advance beyond text-only methods by incorporating multiple modalities of input information to produce a set of conclusive phrases. Traditional multi-modal approaches have been proven to have…

Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to…

Recent advancements in Retrieval-Augmented Language Models (RALMs) have demonstrated their efficacy in knowledge-intensive tasks. However, existing evaluation benchmarks often assume a single optimal approach to leveraging retrieved…