Related papers: Weird Generalization and Inductive Backdoors: New …
We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can…
In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…
Weird generalization is a phenomenon in which models fine-tuned on data from a narrow domain (e.g. insecure code) develop surprising traits that manifest even outside that domain (e.g. broad misalignment)-a phenomenon that prior work has…
Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…
Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…
Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effectively fine-tune LLMs with an extreme reduction in trainable…
While a large body of literature suggests that large language models (LLMs) acquire rich linguistic representations, little is known about whether they adapt to linguistic biases in a human-like way. The present study probes this question…
What makes large language models (LLMs) impressive is also what makes them hard to evaluate: their diversity of uses. To evaluate these models, we must understand the purposes they will be used for. We consider a setting where these…
Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…
Large language models (LLMs) are transforming research on machine learning while galvanizing public debates. Understanding not only when these models work well and succeed but also why they fail and misbehave is of great societal relevance.…
Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…
We investigate the effectiveness of fine-tuning large language models (LLMs) on small medical datasets for text classification and named entity recognition tasks. Using a German cardiology report dataset and the i2b2 Smoking Challenge…
The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…
Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning…
Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…
Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…
In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…
Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…