Related papers: DAFNet: Dynamic Auxiliary Fusion for Sequential Mo…

Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form…

Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful…

Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often…

Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text often suffer from 1) reliance on compute-heavy paraphrasing augmentation and 2) the reversal…

Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within human learning paradigms. However, the potential flaws of…

Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent objects, etc. To handle these challenges, we propose a…

This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concerns become especially…

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…

Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce…

Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We…

Automatic Facial Expression Recognition (FER) has attracted increasing attention in the last 20 years since facial expressions play a central role in human communication. Most FER methodologies utilize Deep Neural Networks (DNNs) that are…

Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an…

Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generated text conflicts with the visual input. Prior work links…

Model editing aims to correct errors and outdated knowledge in the Large language models (LLMs) with minimal cost. Prior research has proposed a variety of datasets to assess the effectiveness of these model editing methods. However, most…

Recent advancements in large language models (LLMs) have significantly improved Natural Language to SQL (NL2SQL) tasks, yet most NL2SQL systems continue to rely on the autoregressive (AR) paradigm. The highly structured nature of SQL makes…

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal…

Paraphrase generation is a pivotal task in natural language processing (NLP). Existing datasets in the domain lack syntactic and lexical diversity, resulting in paraphrases that closely resemble the source sentences. Moreover, these…

Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as…

Supervised fine-tuning (SFT) is widely used to align large language models (LLMs) with information extraction (IE) tasks, such as named entity recognition (NER). However, annotating such fine-grained labels and training domain-specific…