Related papers: Knowledge Updating? No More Model Editing! Just Se…

The proliferation of fake news on social media platforms has exerted a substantial influence on society, leading to discernible impacts and deleterious consequences. Conventional deep learning methodologies employing small language models…

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and…

Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to…

Large Language Models (LLMs) excel at tackling various natural language tasks. However, due to the significant costs involved in re-training or fine-tuning them, they remain largely static and difficult to personalize. Nevertheless, a…

Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cognitive-level modifications while lacking a focus on deeper…

Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach…

With the rapid development of online services, recommender systems (RS) have become increasingly indispensable for mitigating information overload. Despite remarkable progress, conventional recommendation models (CRM) still have some…

Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…

In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across…

Advances in NLP have yielded impressive results for the task of machine reading comprehension (MRC), with approaches having been reported to achieve performance comparable to that of humans. In this paper, we investigate whether…

As powerful tools in Natural Language Processing (NLP), Large Language Models (LLMs) have been leveraged for crafting recommendations to achieve precise alignment with user preferences and elevate the quality of the recommendations. The…

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by…

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context. Previous works studied tuning, decoding algorithms, or locating and editing…

Model editing has been gaining increasing attention over the past few years. For Knowledge Editing in particular, more challenging evaluation datasets have recently been released. These datasets use different methodologies to score the…

Despite their success at many natural language processing (NLP) tasks, large language models still struggle to effectively leverage knowledge for knowledge-intensive tasks, manifesting limitations such as generating incomplete, non-factual,…

The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or…

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual…

The limited reasoning capabilities of small language models (SLMs) cast doubt on their suitability for tasks demanding deep, multi-step logical deduction. This paper introduces a framework called Small Reasons, Large Hints (SMART), which…