Related papers: HIGHT: Hierarchical Graph Tokenization for Molecul…

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. However, LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations in many…

Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However, existing spectral Graph Neural Network (GNN) approaches tailored for…

Language models are increasingly applied to biological sequences like proteins and mRNA, yet their default Euclidean geometry may mismatch the hierarchical structures inherent to biological data. While hyperbolic geometry provides a better…

While large language models (LLMs) excel at understanding and generating plain text, they are not tailored to handle hierarchical text structures or directly predict task-specific properties such as text rating. In fact, selectively and…

Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular…

This research work delves into the manifestation of hallucination within Large Language Models (LLMs) and its consequential impacts on applications within the domain of mental health. The primary objective is to discern effective strategies…

The development of Large Language Models (LLMs) has significantly advanced various AI applications in commercial and scientific research fields, such as scientific literature summarization, writing assistance, and knowledge graph…

GRAFT is a structured multimodal benchmark designed to probe how well LLMs handle instruction following, visual reasoning, and tasks requiring tight visual textual alignment. The dataset is built around programmatically generated charts and…

Sensemaking on a large collection of documents (corpus) is a challenging task often found in fields such as market research, legal studies, intelligence analysis, political science, computational linguistics, etc. Previous works approach…

Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One primary difficulty is that a single image can be generated…

The remarkable success of Large Language Models (LLMs) across diverse tasks has driven the research community to extend their capabilities to molecular applications. However, most molecular LLMs employ adapter-based architectures that do…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics of the text should align with the semantics of the labels…

Large language models achieve impressive results but distinguishing factual reasoning from hallucinations remains challenging. We propose a spectral analysis framework that models transformer layers as dynamic graphs induced by attention,…

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of…

Hallucination has been a major problem for large language models and remains a critical challenge when it comes to multimodality in which vision-language models (VLMs) have to deal with not just textual but also visual inputs. Despite rapid…

Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Autoformalisation helps…

An Achilles heel of Large Language Models (LLMs) is their tendency to hallucinate non-factual statements. A response mixed of factual and non-factual statements poses a challenge for humans to verify and accurately base their decisions on.…

Molecule property prediction has gained significant attention in recent years. The main bottleneck is the label insufficiency caused by expensive lab experiments. In order to alleviate this issue and to better leverage textual knowledge for…

Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks. However, they continue to suffer from significant hallucination issues, including object, attribute, and relational hallucinations.…