Related papers: Model Attribution in LLM-Generated Disinformation:…
As businesses, products, and services spring up around large language models, the trustworthiness of these models hinges on the verifiability of their outputs. However, methods for explaining language model outputs largely fall across two…
Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…
Recent advancements in DeepFake generation, along with the proliferation of open-source tools, have significantly lowered the barrier for creating synthetic media. This trend poses a serious threat to the integrity and authenticity of…
The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be…
As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-training objectives. While prompt-tuning has yielded continuous…
Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of inputs. Gradient integration is a building block in the…
Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the…
Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…
Generative large language models(LLMs) are proficient in solving general problems but often struggle to handle domain-specific tasks. This is because most of domain-specific tasks, such as personalized recommendation, rely on task-related…
Due to the black-box nature of large language models (LLMs) and the realism of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement have become significant. In this context, sourcing…
Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach…
Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to…
Sequential recommendation systems aim to predict users' next likely interaction based on their history. However, these systems face data sparsity and cold-start problems. Utilizing data from other domains, known as multi-domain methods, is…
Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity tasks due to their…
In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated…
The proliferation of fake news has had far-reaching implications on politics, the economy, and society at large. While Fake news detection methods have been employed to mitigate this issue, they primarily depend on two essential elements:…
As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts of the input elements contribute the most to model outputs.…
Although achieving great success, Large Language Models (LLMs) usually suffer from unreliable hallucinations. Although language attribution can be a potential solution, there are no suitable benchmarks and evaluation metrics to attribute…
With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in…
Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space.…