Related papers: Concept Based Continuous Prompts for Interpretable…

Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. Most of these methods organize these vectors in a pool of key-value pairs and use the input image as query…

With the advent of semantic web, various tools and techniques have been introduced for presenting and organizing knowledge. Concept hierarchies are one such technique which gained significant attention due to its usefulness in creating…

Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models provide…

This paper bridges neuroscience and artificial intelligence to propose a cortically inspired blueprint for modular perceptual AI. While current monolithic models such as GPT-4V achieve impressive performance, they often struggle to…

Recent work has shown that generation from a prompted or fine-tuned language model can perform well at semantic parsing when the output is constrained to be a valid semantic representation. We introduce BenchCLAMP, a Benchmark to evaluate…

Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in…

Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we…

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into…

The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. However, although artificial intelligence technology has been…

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While…

Multimodal semantic cues, such as textual descriptions, have shown strong potential in enhancing target perception for tracking. However, existing methods rely on static textual descriptions from large language models, which lack…

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use…

Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…

One of the main methods for computational interpretation of a text is mapping it into a vector in some embedding space. Such vectors can then be used for a variety of textual processing tasks. Recently, most embedding spaces are a product…

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe.…

Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate…

We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a…

Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks. Word…