Related papers: DiffuCOMET: Contextual Commonsense Knowledge Diffu…
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…
In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of…
While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that augments diffusion…
Recent advancements in Language Models (LMs) have demonstrated strong semantic reasoning capabilities, enabling their application in high-level decision-making for autonomous driving (AD). However, LMs operate over discrete token spaces and…
We present DiffExplainer, a novel framework that, leveraging language-vision models, enables multimodal global explainability. DiffExplainer employs diffusion models conditioned on optimized text prompts, synthesizing images that maximize…
Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between events based on…
Empathy is a crucial factor in open-domain conversations, which naturally shows one's caring and understanding to others. Though several methods have been proposed to generate empathetic responses, existing works often lead to monotonous…
The rapid spread of fake news across multimedia platforms presents serious challenges to information credibility. In this paper, we propose a Debunk-and-Infer framework for Fake News Detection(DIFND) that leverages debunking knowledge to…
Commonsense knowledge is crucial for artificial intelligence systems to understand natural language. Previous commonsense knowledge acquisition approaches typically rely on human annotations (for example, ATOMIC) or text generation models…
Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, understanding how commonsense knowledge is represented in…
Text-to-image diffusion models have achieved remarkable fidelity in synthesizing images from explicit text prompts, yet exhibit a critical deficiency in processing implicit prompts that require deep-level world knowledge, ranging from…
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to generate a plausible…
Commonsense knowledge is essential for advancing natural language processing (NLP) by enabling models to engage in human-like reasoning, which requires a deeper understanding of context and often involves making inferences based on implicit…
While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon,…
Many real-world datasets, such as citation networks, social networks, and molecular structures, are naturally represented as heterogeneous graphs, where nodes belong to different types and have additional features. For example, in a…
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store…
Recently, the community has achieved substantial progress on many commonsense reasoning benchmarks. However, it is still unclear what is learned from the training process: the knowledge, inference capability, or both? We argue that due to…
In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…
Most current MKGC approaches are predominantly based on discriminative models that maximize conditional likelihood. These approaches struggle to efficiently capture the complex connections in real-world knowledge graphs, thereby limiting…
Enthymemes are defined as arguments where a premise or conclusion is left implicit. We tackle the task of generating the implicit premise in an enthymeme, which requires not only an understanding of the stated conclusion and premise but…