English
Related papers

Related papers: Perturbation: A simple and efficient adversarial t…

200 papers

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…

Machine Learning · Computer Science 2026-05-29 Hua Li

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,…

Computation and Language · Computer Science 2024-12-16 Tom Kouwenhoven , Max Peeperkorn , Tessa Verhoef

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…

Computation and Language · Computer Science 2021-09-16 Sanchit Sinha , Hanjie Chen , Arshdeep Sekhon , Yangfeng Ji , Yanjun Qi

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…

Artificial Intelligence · Computer Science 2025-06-04 Jinyuan Luo , Zhen Fang , Yixuan Li , Seongheon Park , Ling Chen

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…

Computation and Language · Computer Science 2025-10-27 Marek Kadlčík , Michal Štefánik , Timothee Mickus , Michal Spiegel , Josef Kuchař

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…

Computation and Language · Computer Science 2024-01-24 Dylan Zhang , Curt Tigges , Zory Zhang , Stella Biderman , Maxim Raginsky , Talia Ringer

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…

Computation and Language · Computer Science 2025-09-25 Gemma Boleda

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…

Computation and Language · Computer Science 2025-06-10 Chunyuan Deng , Ruidi Chang , Hanjie Chen

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…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

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…

Computation and Language · Computer Science 2025-02-11 Elias Stengel-Eskin , Peter Hase , Mohit Bansal

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…

Computation and Language · Computer Science 2023-05-12 Hongyi Yuan , Zheng Yuan , Chuanqi Tan , Fei Huang , Songfang Huang

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…

Computation and Language · Computer Science 2025-08-26 Fabian Hoppe , Filip Ilievski , Jan-Christoph Kalo

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…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

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…

Computer Vision and Pattern Recognition · Computer Science 2018-07-09 Omid Poursaeed , Isay Katsman , Bicheng Gao , Serge Belongie

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…

Computation and Language · Computer Science 2019-03-20 Paul Michel , Xian Li , Graham Neubig , Juan Miguel Pino

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…

Machine Learning · Computer Science 2024-10-08 Zhichao Hou , MohamadAli Torkamani , Hamid Krim , Xiaorui Liu

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…

Computation and Language · Computer Science 2018-05-17 Yong Cheng , Zhaopeng Tu , Fandong Meng , Junjie Zhai , Yang Liu

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…

Computation and Language · Computer Science 2026-01-21 Stefano Civelli , Pietro Bernardelle , Nicolò Brunello , Gianluca Demartini

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…

Computation and Language · Computer Science 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari
‹ Prev 1 3 4 5 6 7 10 Next ›