Researchers from the City University of Hong Kong and Huawei Noah's Ark Lab have developed an innovative recommender system that takes advantage of Large Language Models (LLMs) like ChatGPT and Claude. The model, dubbed UniLLMRec, leverages the inherent zero-shot learning capabilities of LLMs, eliminating the need for traditional training and fine-tuning. Consequently, it offers an…
Within the field of Natural Language Processing (NLP), resolving references is a critical challenge. It involves identifying the context of specific words or phrases, pivotal to both understanding and successfully managing diverse forms of context. These can range from previous dialogue turns in conversation to non-conversational elements such as user screen entities or background processes.
Existing…
The need for speed and precision in today's digitally-fueled arena is ever-increasing, making it a challenge for search engines to meet these expectations. Traditional retrieval models present a trade-off between speed, accuracy, and computational cost. To address this, researchers from the University of Glasgow have offered a creative solution known as shallow Cross-Encoders. These small…
Large Language Models (LLMs) are widely used in complex reasoning tasks across various fields. But, their construction and optimization demand considerable computational power, particularly when pretraining on large datasets. To mitigate this, researchers have proposed scaling equations showing the relationship between pretraining loss and computational effort.
However, new findings suggest these rules may not thoroughly represent…
Large Language Models (LLMs) require safety tuning to ensure alignment with human values. However, even those tuned for safety are susceptible to jailbreaking—errant behavior that escapes designed safety measures. Even benign data, free of harmful content, can lead to safety degradation, an issue recently studied by researchers from Princeton University's Princeton Language and Intelligence (PLI).
The…
The fast-paced evolution of artificial intelligence, particularly Vision Language Models (VLMs), presents challenges in ensuring their reliability and trustworthiness. These VLMs integrate visual and textual understanding, however, their increasing sophistication has brought into focus their ability to detect and not respond to unsolvable or irrelevant questions— an aspect known as Unsolvable Problem Detection (UPD).
UPD…
Natural Language Processing (NLP) has transformed with the advent of Transformer models. The document generation and summarization, machine translation, and speech recognition abilities of Transformers have exhibited significant progress. Their dominance is specifically seen in large language models (LLMs) that deal with more complex tasks through upscaling transformer architecture. However, the growth of the Transformer…
Artificial intelligence (AI) is advancing at a rapid pace, with breakthroughs in natural language processing (NLP) seen in virtual assistants and language models. However, as these systems become more sophisticated, they also become harder to understand, a concern in critical sectors such as healthcare, finance, and criminal justice. Researchers from Imperial College London have now…
Researchers have noted gaps in the evaluation methods for Large Vision Language Models (LVLMs). Primarily, they note that evaluations overlook the potential of visual content being unnecessary for many samples, as well as the risk of unintentional data leakage during training. They also indicate the limitations of single-task benchmarks for accurately assessing the multi-modal capabilities…
From a young age, humans showcase an impressive ability to merge their knowledge and skills in novel ways to construct solutions to problems. This principle of compositional reasoning is a critical aspect of human intelligence that allows our brains to create complex representations from simpler parts. Unfortunately, AI systems have struggled to replicate this capability…
Artificial intelligence's progression in recent years has seen an increased focus on the development of multi-agent simulators. This technology aims to create virtual environments where AI agents can interact with their surroundings and each other, providing researchers with a unique opportunity to study social dynamics, collective behavior, and the development of complex systems. However, most…
The Dynamic Retrieval Augmented Generation (RAG) approach is designed to boost the performance of Large Language Models (LLMs) through determining when and what external information to retrieve during text generation. However, the current methods to decide when to recover data often rely on static rules and tend to limit retrieval to recent sentences or tokens,…