Related papers: Attention Overflow: Language Model Input Blur duri…
We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injection, Overflow arises under ordinary interaction settings…
Large-language Models (LLMs) have been extremely successful at tasks like complex dialogue understanding, reasoning and coding due to their emergent abilities. These emergent abilities have been extended with multi-modality to include…
Large Language Models (LLMs) have demonstrated remarkable capabilities in comprehending and analyzing lengthy sequential inputs, owing to their extensive context windows that allow processing millions of tokens in a single forward pass.…
Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…
Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely solely on content features, limiting their recommendation…
In large language models (LLM)-based recommendation systems (LLM-RSs), accurately predicting user preferences by leveraging the general knowledge of LLMs is possible without requiring extensive training data. By converting recommendation…
Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify…
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…
Serendipity-oriented recommender systems aim to counteract over-specialization in user preferences. However, evaluating a user's serendipitous response towards a recommended item can be challenging because of its emotional nature. In this…
Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…
The paper underscores the significance of Large Language Models (LLMs) in reshaping recommender systems, attributing their value to unique reasoning abilities absent in traditional recommenders. Unlike conventional systems lacking direct…
Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and…
Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable,…
Traditional interventions for academic procrastination often fail to capture the nuanced, individual-specific factors that underlie them. Large language models (LLMs) hold immense potential for addressing this gap by permitting open-ended…
Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…
Planning for both immediate and long-term benefits becomes increasingly important in recommendation. Existing methods apply Reinforcement Learning (RL) to learn planning capacity by maximizing cumulative reward for long-term recommendation.…
Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information,…
Recent work has shown that large pretrained Language Models (LMs) can not only perform remarkably well on a range of Natural Language Processing (NLP) tasks but also start improving on reasoning tasks such as arithmetic induction, symbolic…
Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…
Sequential recommendation aims to predict users' next interaction with items based on their past engagement sequence. Recently, the advent of Large Language Models (LLMs) has sparked interest in leveraging them for sequential…