Related papers: Large Language Models Sometimes Generate Purely Ne…
Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…
Recurrent neural networks can learn to predict upcoming words remarkably well on average; in syntactically complex contexts, however, they often assign unexpectedly high probabilities to ungrammatical words. We investigate to what extent…
Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…
This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…
We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the…
Large language models (LLMs) have a surprising failure: when trained on "A has a feature B", they do not generalize to "B is a feature of A", which is termed the Reversal Curse. Even when training with trillions of tokens this issue still…
The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…
Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…
With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…
Large language models must balance their weight-encoded knowledge with in-context information from prompts to generate accurate responses. This paper investigates this interplay by analyzing how models of varying capacities within the same…
Language models can achieve high accuracy on natural language tasks such as NLI, but performance suffers on manually created adversarial examples. We investigate the performance of a language model trained on the Stanford Natural Language…
Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…
Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these…
The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective…
Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…
Word-level textual adversarial attacks have demonstrated notable efficacy in misleading Natural Language Processing (NLP) models. Despite their success, the underlying reasons for their effectiveness and the fundamental characteristics of…
Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…
Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing…
Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…