Related papers: CiteBART: Learning to Generate Citations for Local…

Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. In this work, our aim is to allow LLMs to generate text with citations, improving their factual…

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise,…

Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single…

Prediction of the future performance of academic journals is a task that can benefit a variety of stakeholders including editorial staff, publishers, indexing services, researchers, university administrators and granting agencies. Using…

Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current methods often depend on large replay buffers or heavily…

Citation networks are critical in modern science, and predicting which previous papers (candidates) will a new paper (query) cite is a critical problem. However, the roles of a paper's citations vary significantly, ranging from foundational…

Large language models (LLMs) present a promising yet challenging frontier for automated source citation in scientific communication. Previous approaches to citation generation have been limited by citation ambiguity and LLM…

Citation recommendation systems have attracted much academic interest, resulting in many studies and implementations. These systems help authors automatically generate proper citations by suggesting relevant references based on the text…

Despite significant advancements in multimodal reasoning tasks, existing Large Vision-Language Models (LVLMs) are prone to producing visually ungrounded responses when interpreting associated images. In contrast, when humans embark on…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform new tasks by conditioning on prompts with relevant information. Retrieval-Augmented Generation (RAG) enhances ICL by incorporating retrieved documents into the LLM's…

Multilingual Large Language Models(MLLMs) demonstrate strong generalization across languages, yet they remain prone to hallucinations, especially in low-resource languages, due to training data imbalances. These hallucinations, which…

Citation recommendation systems for the scientific literature, to help authors find papers that should be cited, have the potential to speed up discoveries and uncover new routes for scientific exploration. We treat this task as a ranking…

Predicting the number of citations of scholarly documents is an upcoming task in scholarly document processing. Besides the intrinsic merit of this information, it also has a wider use as an imperfect proxy for quality which has the…

Citation intention Classification (CIC) tools classify citations by their intention (e.g., background, motivation) and assist readers in evaluating the contribution of scientific literature. Prior research has shown that pretrained language…

We introduce LITcoder, an open-source library for building and benchmarking neural encoding models. Designed as a flexible backend, LITcoder provides standardized tools for aligning continuous stimuli (e.g., text and speech) with brain…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of…

We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired by both recent results on neural networks with wide local…

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text…