相关论文: The Mosaic Memory of Large Language Models

Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal…

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

How can pretrained language models (PLMs) learn factual knowledge from the training set? We investigate the two most important mechanisms: reasoning and memorization. Prior work has attempted to quantify the number of facts PLMs learn, but…

In recent years, Large Language Models (LLMs) have gained significant popularity due to their ability to generate human-like text and their potential applications in various fields, such as Software Engineering. LLMs for Code are commonly…

The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over…

The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve problems. On the…

Large Language Models (LLMs) have become integral to various software engineering tasks, including code generation, bug detection, and repair. To evaluate model performance in these domains, numerous bug benchmarks containing real-world…

Large language models (LLMs) can store a vast amount of world knowledge, often extractable via question-answering (e.g., "What is Abraham Lincoln's birthday?"). However, do they answer such questions based on exposure to similar questions…

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…

Recent research has highlighted the importance of dataset size in scaling language models. However, large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its…

Understanding how humans conceptualize and categorize natural objects offers critical insights into perception and cognition. With the advent of Large Language Models (LLMs), a key question arises: can these models develop human-like object…

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled…

Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent downstream tasks such as question answering,…

Large language models (LLMs) have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy)…

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…

Recent advances in large language models (LLMs) have revolutionized natural language processing, yet evaluating their intrinsic linguistic understanding remains challenging. Moving beyond specialized evaluation tasks, we propose an…

Ashery et al. recently argue that large language models (LLMs), when paired to play a classic "naming game," spontaneously develop linguistic conventions reminiscent of human social norms. Here, we show that their results are better…

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…

Large language models (LLMs) suffer from forgetting of upstream knowledge when fine-tuned. Despite efforts on mitigating forgetting, few have investigated how forgotten upstream examples are dependent on newly learned tasks. Insights on…

Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained…