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

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…

Machine unlearning is a critical area of research aimed at safeguarding data privacy by enabling the removal of sensitive information from machine learning models. One unique challenge in this field is catastrophic unlearning, where erasing…

Text representation models are prone to exhibit a range of societal biases, reflecting the non-controlled and biased nature of the underlying pretraining data, which consequently leads to severe ethical issues and even bias amplification.…

While large language models (LLMs) have become the de facto framework for literature-related tasks, they still struggle to function as domain-specific literature agents due to their inability to connect pieces of knowledge and reason across…

As artificial neural networks, and specifically large language models, have improved rapidly in capabilities and quality, they have increasingly been deployed in real-world applications, from customer service to Google search, despite the…

Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large…

Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties…

In the multi-turn interaction schema, large language models (LLMs) can leverage user feedback to enhance the quality and relevance of their responses. However, evaluating an LLM's ability to incorporate user refutation feedback is crucial…

We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval…

Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge updates without costly retraining are a major challenge. This problem is particularly challenging in lifelong…

Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate…

The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-world long texts, making it difficult to exclude the…

We propose Autolearn, a framework that enables language models to learn from documents they read, with no external supervision. Passages that produce anomalously high per-token loss are flagged, verified through a self-generated Q&A chain,…

Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. Existing utility-centric unlearning metrics…

Automated radiology report generation (R2Gen) has advanced significantly, introducing challenges in accurate evaluation due to its complexity. Traditional metrics often fall short by relying on rigid word-matching or focusing only on…

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed. However, how to take action to address these patterns is not always…

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…