Related papers: CaPE: Contrastive Parameter Ensembling for Reducin…

While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come in many forms, and there is no universally accepted…

Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models…

We address the problem of unsupervised abstractive summarization of collections of user generated reviews with self-supervision and control. We propose a self-supervised setup that considers an individual document as a target summary for a…

E-commerce stores collect customer feedback to let sellers learn about customer concerns and enhance customer order experience. Because customer feedback often contains redundant information, a concise summary of the feedback can be…

With recent advancements in deep learning methods, automatically learning deep features from the original data is becoming an effective and widespread approach. However, the hand-crafted expert knowledge-based features are still insightful.…

Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with human judgments. Secondly, each metric has well known blind spots to…

Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by single-perspective analysis, static reasoning pathways, and a susceptibility to hallucination when…

Large Vision-Language Models (LVLMs) have achieved impressive results across various cross-modal tasks. However, hallucinations, i.e., the models generating counterfactual responses, remain a challenge. Though recent studies have attempted…

Multi-modal Large Language Models (MLLMs) demonstrate remarkable success across various vision-language tasks. However, they suffer from visual hallucination, where the generated responses diverge from the provided image. Are MLLMs…

We present Causal Posterior Estimation (CPE), a novel method for Bayesian inference in simulator models, i.e., models where the evaluation of the likelihood function is intractable or too computationally expensive, but where one can…

In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing…

Conditional Neural Processes~(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. CNPs, however, have limited expressivity for high-dimensional observations, since their…

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the…

Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document. In this paper, we propose Constrained Abstractive Summarization (CAS), a general…

Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task…

Retrieval-Augmented Generation (RAG) models frequently encounter hallucination phenomena when integrating external information with internal parametric knowledge. Empirical studies demonstrate that the disequilibrium between external…

Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent…

The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models…

Pretrained cross-modal models, for instance, the most representative CLIP, have recently led to a boom in using pre-trained models for cross-modal zero-shot tasks, considering the generalization properties. However, we analytically discover…

Neural image classifiers can often learn to make predictions by overly relying on non-predictive features that are spuriously correlated with the class labels in the training data. This leads to poor performance in real-world atypical…