相关论文: Rebuilding ROME : Resolving Model Collapse during …

Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing techniques exhibit…

Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor generalization to newly added documents, often failing to…

While large pre-trained models have enabled impressive results on a variety of downstream tasks, the largest existing models still make errors, and even accurate predictions may become outdated over time. Because detecting all such failures…

In the era of proliferation of large language and image generation models, the phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time,…

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain…

This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators'…

This paper presents a novel model protection paradigm ModelLock that locks (destroys) the performance of a model on normal clean data so as to make it unusable or unextractable without the right key. Specifically, we proposed a…

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current…

Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct…

Tool-using agent systems powered by large language models (LLMs) are increasingly deployed across web, app, operating-system, and transactional environments. Yet existing safety benchmarks still emphasize explicit risks, potentially…

Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training which is inefficient…

Most existing sequence generation models produce outputs in one pass, usually left-to-right. However, this is in contrast with a more natural approach that humans use in generating content; iterative refinement and editing. Recent work has…

Many beloved programming systems are image-based: self-contained worlds that persist both code and data in a single file. Examples include Smalltalk, LISP, HyperCard, Flash, and spreadsheets. Image-based programming avoids much of the…

Large Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HDL generation struggle when handling complex tasks. We introduce a suite of…

The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky --…

Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures…

Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by…

Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mitigating these challenges in a cost-effective manner.…

Model merging is a technique that combines multiple finetuned models into a single model without additional training, allowing a free-rider to cheaply inherit specialized capabilities. This study investigates methodologies to suppress…

Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing.…