相关论文: RippleBench: Capturing Ripple Effects Using Existi…

Machine unlearning aims to remove the influence of specific training samples from a trained model without full retraining. While prior work has largely focused on privacy-motivated settings, we recast unlearning as a general-purpose tool…

Verifying the authenticity of AI-generated text has become increasingly important with the rapid advancement of large language models, and unbiased watermarking has emerged as a promising approach due to its ability to preserve output…

Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge from a model without full retraining. A major bottleneck in…

Large Language Models have revolutionized numerous tasks with their remarkable efficacy. However, editing these models, crucial for rectifying outdated or erroneous information, often leads to a complex issue known as the ripple effect in…

The static knowledge representations of large language models (LLMs) inevitably become outdated or incorrect over time. While model-editing techniques offer a promising solution by modifying a model's factual associations, they often…

As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning methods have emerged in response, they…

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…

We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational…

With the passage of the Right to Be Forgotten (RTBF) regulations and the scaling up of language model training datasets, research on model unlearning in large language models (LLMs) has become more crucial. Before the era of LLMs, machine…

Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a…

Despite recent advances in inversion and instruction-based image editing, existing approaches primarily excel at editing single, prominent objects but significantly struggle when applied to complex scenes containing multiple entities. To…

Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging. Benchmarks derived from published studies and human annotations inherit publication bias,…

We study the task of automatically finding evidence relevant to hypotheses in biomedical papers. Finding relevant evidence is an important step when researchers investigate scientific hypotheses. We introduce EvidenceBench to measure models…

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to…

Reasoning about events and tracking their influences is fundamental to understanding processes. In this paper, we present EIGEN - a method to leverage pre-trained language models to generate event influences conditioned on a context, nature…

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs --…