相关论文: Vectors Are Not Neutral: Sensitive-Information Inf…

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…

Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networks. Discarding noisy labels avoids a harmful memorization,…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Infostealers exfiltrate credentials, session cookies, and sensitive data from infected systems. With over 29 million stealer logs reported in 2024, manual analysis and mitigation at scale are virtually unfeasible/unpractical. While most…

Recent studies show that neural retrievers often display source bias, favoring passages generated by LLMs over human-written ones, even when both are semantically similar. This bias has been considered an inherent flaw of retrievers,…

Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid…

Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from…

Large Language Models (LLMs) have shown improved generation performance through retrieval-augmented generation (RAG) following the retriever-reader paradigm, which supplements model inputs with externally retrieved knowledge. However, prior…

Label smoothing is a regularization technique for neural networks. Normally neural models are trained to an output distribution that is a vector with a single 1 for the correct prediction, and 0 for all other elements. Label smoothing…

Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but its reliability under resource-constrained, privacy-sensitive deployments remains…

Generative models can generate photorealistic images at scale. This raises urgent concerns about the ability to detect synthetically generated images and attribute these images to specific sources. While watermarking has emerged as a…

Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences…

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…

Memory-efficient large language models are good at refining text input for better readability. However, controllability is a matter of concern when it comes to text generation tasks with long inputs, such as multi-document summarization. In…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

The extraction of critical patient information from Electronic Health Records (EHRs) poses significant challenges due to the complexity and unstructured nature of the data. Traditional machine learning approaches often fail to capture…

Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authorship attribution, raising legal and ethical concerns around…

Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting their learned representations. In this paper, we study the…

Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language to gain a concise view of their content. In the present day,…