相关论文: Assistive Recipe Editing through Critiquing
Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through…
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like…
Food recommendation has become an important means to help guide users to adopt healthy dietary habits. Previous works on food recommendation either i) fail to consider users' explicit requirements, ii) ignore crucial health factors (e.g.,…
Research on food image understanding using recipe data has been a long-standing focus due to the diversity and complexity of the data. Moreover, food is inextricably linked to people's lives, making it a vital research area for practical…
Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact and avoiding unnecessary modifications. However,…
Just as user preferences change with time, item reviews also reflect those same preference changes. In a nutshell, if one is to sequentially incorporate review content knowledge into recommender systems, one is naturally led to dynamical…
AI-generated text is proliferating across domains, from creative writing and journalism to marketing content and scientific articles. Models can follow user-provided instructions to generate coherent and grammatically correct outputs but in…
Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals…
Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source…
In the rapidly evolving landscape of online recipe sharing within a globalized context, there has been a notable surge in research towards comprehending and generating food recipes. Recent advancements in large language models (LLMs) like…
Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process, today's language models are trained to generate only the…
Humans follow criteria when they execute tasks, and these criteria are directly used to assess the quality of task completion. Therefore, having models learn to use criteria to provide feedback can help humans or models to perform tasks…
Poor diet and nutrition in the United States has immense financial and health costs, and development of new tools for diet planning could help families better balance their financial and temporal constraints with the quality of their diet…
Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…
As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rectify potential errors. The question arises naturally: can we…
Argument mining aims to detect all possible argumentative components and identify their relationships automatically. As a thriving task in natural language processing, there has been a large amount of corpus for academic study and…
Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM…
Despite significant advances in large language models, personalizing them for individual decision-makers remains an open problem. Here, we introduce a synthetic-organic supervision pipeline that transforms raw judicial decisions into…
Recent work has explored the capability of large language models (LLMs) to identify and correct errors in LLM-generated responses. These refinement approaches frequently evaluate what sizes of models are able to do refinement for what…