Related papers: Perturbation: A simple and efficient adversarial t…
Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…
Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…
Interpretability methods like Integrated Gradient and LIME are popular choices for explaining natural language model predictions with relative word importance scores. These interpretations need to be robust for trustworthy NLP applications…
Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own…
Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…
This paper investigates the ability of transformer-based models to learn structural recursion from examples. Recursion is a universal concept in both natural and formal languages. Structural recursion is central to the programming language…
Since the middle of the 20th century, a fierce battle is being fought between symbolic and distributed approaches to language and cognition. The success of deep learning models, and LLMs in particular, has been alternatively taken as…
Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning, aim to apply pointwise control within the concept subspace…
Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…
Large language models (LLMs) are susceptible to persuasion, which can pose risks when models are faced with an adversarial interlocutor. We take a first step towards defending models against persuasion while also arguing that defense…
Language models with the Transformers structure have shown great performance in natural language processing. However, there still poses problems when fine-tuning pre-trained language models on downstream tasks, such as over-fitting or…
Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and…
Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for…
Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…
Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…
This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…
Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with…
Predicting problem-difficulty in large language models (LLMs) refers to estimating how difficult a task is according to the model itself, typically by training linear probes on its internal representations. In this work, we study the…
Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…